| 1 |
Web Application for Automatic Code Generator using Structured Flowchart |
|
|
ชาญชัย ศุภอรรถกร |
Q3 |
นานาชาติ |
|
| 2 |
Vector field reconstruction via quaternionic setting |
|
|
พัชรี วงษาสนธิ์ |
Q3 |
นานาชาติ |
|
| 3 |
0 |
|
|
ปิยะนันท์ พนากานต์ |
Q2 |
นานาชาติ |
|
| 4 |
3D cone beam reconstruction formula by using cylindrical coordinates |
|
|
สุพจน์ สีบุตร |
Q3 |
นานาชาติ |
|
| 5 |
Trip Basket: Web Characterization for Smart Tourism |
|
|
วาสนา เหง้าเกษ |
Q3 |
นานาชาติ |
|
| 6 |
Development of the Edible and Poisonous
Mushrooms Classification Model by using the
Feature Selection and the Decision Tree
Techniques |
Development of the Edible and Poisonous
Mushrooms Classification Model by using the
Feature Selection and the Decision Tree
Techniques |
This research aims to develop a classification model for edible and poisonous mushrooms by applying the feature selection approach together with the decision tree technique. Two feature selection methods were applied, including 1) Chi-square and 2) Information Gain, while the effectiveness of the model was compared by three decision tree methods such as Iterative Dichotomiser3, C4.5 and Random Forest. The data used for classifying the edible and poisonous mushrooms derived from the Encyclopedia of Thai mushrooms and the book entitled “Diversity of Mushrooms and Macrofungi in Thailand”. The results of the model’s effectiveness evaluation revealed that the model using the Information Gain technique alongside with the Random Forest technique provided the most accurate classification outcomes at 94.19%; therefore, this model could be further applied in the future studies. |
วงกต ศรีอุไร |
Q4 |
นานาชาติ |
|
| 7 |
Convergence Theorems of the Modified SP-Iteration for $G$-Asymptotically Nonexpansive Mappings with Directed Grahps |
Convergence Theorems of the Modified SP-Iteration for $G$-Asymptotically Nonexpansive Mappings with Directed Grahps |
In this paper, weak and strong convergence theorems of the modified SP-iteration are established for three G-asymptotically nonexpansive mappings in Banach spaces. We give some numerical example for supporting our main theorem and compare convergence rate between the modified SP-iteration and the modified Noor iteration. |
รตนกร วัฒนทวีกุล |
Q4 |
นานาชาติ |
|
| 8 |
Matrix operators on function-valued function spaces |
Matrix operators on function-valued function spaces |
We study spaces of continuous-function-valued functions that have the property that composition with evaluation functionals induce weak∗ to norm continuous maps to lp space (p∈(1,∞)). Versions of H\"older's inequality and Riesz representation theorem are proved to hold on these spaces. We prove a version of Dixmier's theorem for spaces of function-valued matrix operators on these spaces, and an analogue of the trace formula for operators on Hilbert spaces. When the function space is taken to be the complex field, the spaces are just the lp spaces and the well-known classical theorems follow from our results. |
ฐิตารีย์ วุฒิจิรัฐิติกาล |
Q2 |
นานาชาติ |
|
| 9 |
การพัฒนาระบบการค้าส่งและบริหารลูกหนี้ กรณีศึกษาการประเมินความเสี่ยงในการชําระหนี้ |
|
|
ชุมพร หลินหะตระกูล |
Q1 |
นานาชาติ |
|
| 10 |
Numerical simulation of heat transfer over a torus rotating about its centerline |
Numerical simulation of heat transfer over a torus rotating about its centerline |
The heat transfer characteristics of axisymmetric flow past a rotating torus in viscous incompressible fluid have been investigated numerically. The torus surface rotates about its centerline with constant velocity. The governing equations in a toroidal coordinate system are solved by using a finite difference method for ranges of parameters: Reynolds number 20 40 Re ; Prandtl number 0 7 100 . Pr ; rotational speed 0 1 9 . ; and fixed aspect ratio Ar 2. The heat transfer characteristics are presented in terms of the isotherm patterns, local Nusselt numbers, and average Nusselt numbers. Variation of the local Nusselt number on the torus surface shows the effect of the Prandtl number and rotational speed on heat transfer from a torus in the flow regime. Torus rotation is an efficient Nusselt number reduction or torus surface temperature enhancement technique. |
ไพรินทร์ สุวรรณศรี |
Q4 |
นานาชาติ |
|
| 11 |
GoF Design Patterns in a Smart City System |
|
|
วาสนา เหง้าเกษ |
Q2 |
นานาชาติ |
ชื่อวารสาร
-
Journal of Computers
|
| 12 |
The Application of the Multi-Layer Perceptron Neural Network Technique for Developing the Career-Suggestion Simulation Model for Undergraduate Students |
The Application of the Multi-Layer Perceptron Neural Network Technique for Developing the Career-Suggestion Simulation Model for Undergraduate Students |
The goal of the study is to develop the career-suggestion simulation model for newly graduated students with a bachelor’s degree in information technology by using the Multi-Layer Perceptron Neural Network technique. Due to the lack of data collected for developing the model from a limited data sets, the researcher decided to apply the Resample technique to solve the problem of the data set with imbalanced prediction outputs by adjusting the imbalance of the data set starting from 100% to 500%. Subsequently, the Multi-Layer Perceptron Neural Network technique was applied for developing the career-suggestion simulation model. There were two approaches used for testing the effectiveness of the simulation model, including the 5-fold cross validation and 10-fold cross validation techniques. The results of the simulation model’s effectiveness test using the 10-fold cross validation technique with the adjusted resample of 500% and the Multi-Layer Perceptron Neural Network technique provide the accuracy of 93.62% which is higher than the career-suggestion simulation model which applies the MultiLayer Perceptron Neural Network technique alone. The research findings reveal that the simulation model can be used as the prototype of the career-suggestion simulation model for newly graduated students with a bachelor’s degree in information technology. |
วงกต ศรีอุไร |
Q4 |
นานาชาติ |
|
| 13 |
Second-hand Cars Recommender System Model
using the SMOTE and the Random Forest
Technique |
Second-hand Cars Recommender System Model
using the SMOTE and the Random Forest
Technique |
This article is object to develop a model for a second-hand cars recommender system towards the use of the SMOTE approach together with the Random Forest technique. The research team has modified the imbalance of the data by employing the SMOTE method to increase the amount of data to 400% and applying the Random Forest technique to create a decision tree for second-hand car recommendations. After evaluating the model’s effectiveness by using the 10- fold validation method, the findings revealed that the second-hand recommender system model applying the SMOTE approach and the Random Forest technique provided an accuracy of 98.84%, a precision of 98.89%, a recall of 98.80% and an F1 score of 98.80%; the overall scores of the model’s effectiveness were higher than of the model using only the Random Forest technique. This indicates that the model can be practically used for recommending second-hand cars. |
วงกต ศรีอุไร |
ยังไม่มีระดับ Quartile Scor |
นานาชาติ |
|
| 14 |
A Fast Fixed-Point Algorithm for Convex Minimization Problems and Its Application in Image Restoration Problems |
A Fast Fixed-Point Algorithm for Convex Minimization Problems and Its Application in Image Restoration Problems |
In this paper, we introduce a new iterative method using an inertial technique for approximating a common fixed point of an infinite family of nonexpansive mappings in a Hilbert space. The proposed method’s weak convergence theorem was established under some suitable conditions. Furthermore, we applied our main results to solve convex minimization problems and image restoration problems. |
รตนกร วัฒนทวีกุล |
Q1 |
นานาชาติ |
|
| 15 |
An Accelerated Fixed-Point Algorithm with an Inertial Technique for a Countable Family of G-Nonexpansive Mappings Applied to Image Recovery |
An Accelerated Fixed-Point Algorithm with an Inertial Technique for a Countable Family of G-Nonexpansive Mappings Applied to Image Recovery |
Many authors have proposed fixed-point algorithms for obtaining a fixed point of G-nonexpansive mappings without using inertial techniques. To improve convergence behavior, some accelerated fixed-point methods have been introduced. The main aim of this paper is to use a coordinate affine structure to create an accelerated fixed-point algorithm with an inertial technique for a countable family of G-nonexpansive mappings in a Hilbert space with a symmetric directed graph G and prove the weak convergence theorem of the proposed algorithm. As an application, we apply our proposed algorithm to solve image restoration and convex minimization problems. The numerical experiments show that our algorithm is more efficient than FBA, FISTA, Ishikawa iteration, S-iteration, Noor iteration and SP-iteration. |
รตนกร วัฒนทวีกุล |
Q1 |
นานาชาติ |
|
| 16 |
Python-based simulations of the probabilistic behavior of random events for secondary school students |
Python-based simulations of the probabilistic behavior of random events for secondary school students |
Simulation modeling is an effective tool for solving problems that cannot be explained analytically or when data cannot be collected. This is done by simulating the observed behavior of a problem under study using a computer program. In math education, this can develop knowledge and fundamental competencies of simulation modeling at a higher level and foster its applications in everyday life. This study created learning activities for secondary school students to simulate the probabilistic behavior of random events using Python. 28 grade 12 students took part in these activities using appropriate scaffolding strategies and a powerful mathematical tool, Python. After completing the activities, student competency in simulating the probabilistic behavior of random events with Python was evaluated using rubrics and the factors of student enjoyment, perceived value, interest, and self-efficacy were determined through a Likert-scale questionnaire. The assessment results showed that the activities had a positive effect on student competencies and emotions. The outcomes of the study can serve guidelines for teachers who are interested in expanding the results for further student development. © 2022. by the authors; licensee Modestum. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/). |
สุพจน์ สีบุตร |
Q1 |
นานาชาติ |
|
| 17 |
Swarming Computational Techniques for the Influenza Disease System |
Swarming Computational Techniques for the Influenza Disease System |
The current study relates to designing a swarming computational paradigm to solve the influenza disease system (IDS). The nonlinear system’s mathematical form depends upon four classes: susceptible individuals, infected people, recovered individuals and cross-immune people. The solutions of the IDS are provided by using the artificial neural networks (ANNs) together with the swarming computational paradigm-based particle swarm optimization (PSO) and interior-point scheme (IPA) that are the global and local search approaches. The ANNs-PSO-IPA has never been applied to solve the IDS. Instead a merit function in the sense of mean square error is constructed using the differential form of each class of the IDS and then optimized by the PSOIPA. The correctness and accuracy of the scheme are observed to perform the comparative analysis of the obtained IDS results with the Adams solutions (reference solutions). An absolute error in suitable measures shows the precision of the proposed ANNs procedures and the optimization efficiency of the PSOIPA. Furthermore, the reliability and competence of the proposed computing method are enhanced through the statistical performances. |
ศักดิ์ดา น้อยนาง |
Q1 |
นานาชาติ |
|
| 18 |
Swarming Computational Efficiency to Solve a Novel Third-Order Delay Differential Emden-Fowler System |
Swarming Computational Efficiency to Solve a Novel Third-Order Delay Differential Emden-Fowler System |
The purpose of this research is to construct an integrated neuro swarming scheme using the procedures of the artificial neural networks (ANNs) with the use of global search particle swarm optimization (PSO) along with the competent local search interior-point programming (IPP) called as ANN-PSOIPP. The proposed computational scheme is implemented for the numerical simulations of the third order nonlinear delay differential Emden-Fowler model (TON-DD-EFM). The TON-DD-EFM is based on two types along with the particulars of shape factor, delayed terms, and singular points. A merit function is performed using the optimization of PSOIPP to find the solutions to the TON-DD-EFM. The effectiveness of the ANN-PSOIPP is certified through the comparison with the exact results for solving four examples of the TON-DD-EFM. The scheme’s efficiency is observed by performing the absolute error in suitable measures found around 10−04 to 10−07. Furthermore, the statistical-based assessments for 100 trials are provided to compute the accuracy, stability, and constancy of the ANN-PSOIPP for solving the TON-DD-EFM. |
ศักดิ์ดา น้อยนาง |
Q1 |
นานาชาติ |
|
| 19 |
A Novel Stochastic Framework for the MHD Generator in Ocean |
A Novel Stochastic Framework for the MHD Generator in Ocean |
This work aims to study the nonlinear ordinary differential equations (ODEs) system of magnetohydrodynamic (MHD) past over an inclined plate using Levenberg-Marquardt backpropagation neural networks (LMBNNs). The stochastic procedures LMBNNs are provided with three categories of sample statistics, testing, training, and verification. The nonlinear MHD system past over an inclined plate is divided into three profiles, dimensionless momentum, species (salinity), and energy (heat) conservations. The data is applied 15%, 10%, and 75% for validation, testing, and training to solve the nonlinear system of MHD past over an inclined plate. A reference data set is designed to compare the obtained and proposed solutions for the MHD system. The plots of the absolute error (AE) are provided to check the accuracy and precision of the considered nonlinear system of MHD. The obtained numerical solutions of the nonlinear magnetohydrodynamic system have been considered to reduce the mean square error (MSE). For the capability, dependability, and aptitude of the stochastic LMBNNs procedure, the numerical performances are provided to authenticate the relative arrangements of MSE, error histograms (EHs), state transitions (STs), correlation, and regression. |
ศักดิ์ดา น้อยนาง |
Q1 |
นานาชาติ |
|
| 20 |
An accelerated common fixed point algorithm for a countable family of G-nonexpansive mappings with applications to image recovery |
An accelerated common fixed point algorithm for a countable family of G-nonexpansive mappings with applications to image recovery |
In this paper, we define a new concept of left and right coordinate affine of a directed graph and then employ it to introduce a new accelerated common fixed point algorithm for a countable family of G-nonexpansive mappings in a real Hilbert space with a graph. We prove, under certain conditions, weak convergence theorems for the proposed algorithm. As applications, we also apply our results to solve convex minimization and image restoration problems. Moreover, we show that our algorithm provides better convergence behavior than other methods in the literature. |
รตนกร วัฒนทวีกุล |
Q1 |
นานาชาติ |
|
| 21 |
A New Accelerated Fixed-Point Algorithm for Classification and Convex Minimization Problems in Hilbert Spaces with Directed Graphs |
A New Accelerated Fixed-Point Algorithm for Classification and Convex Minimization Problems in Hilbert Spaces with Directed Graphs |
A new accelerated algorithm for approximating the common fixed points of a countable family of G-nonexpansive mappings is proposed, and the weak convergence theorem based on our main results is established in the setting of Hilbert spaces with a symmetric directed graph G. As an application, we apply our results for solving classification and convex minimization problems. We also apply our proposed algorithm to estimate the weight connecting the hidden layer and output layer in a regularized extreme learning machine. For numerical experiments, the proposed algorithm gives a higher performance of accuracy of the testing set than that of FISTA-S, FISTA, and nAGA. |
รตนกร วัฒนทวีกุล |
Q1 |
นานาชาติ |
|
| 22 |
Representations of modified type 2 degenerate poly-Bernoulli polynomials |
Representations of modified type 2 degenerate poly-Bernoulli polynomials |
Research on the degenerate versions of special polynomials provides a new area, introducing the λ-analogue of special polynomials and numbers, such as λ-Sheffer polynomials. In this paper, we propose a new variant of type 2 Bernoulli polynomials and numbers by modifying a generating function. Then we derive explicit expressions and their representations that provide connections among existing λ-Sheffer polynomials. Also, we provide the explicit representations of the proposed polynomials in terms of the degenerate Lah-Bell polynomials and the higher-order degenerate derangement polynomials to confirm the presented identities. © 2022 the Author(s), licensee AIMS Press. |
พัชรี วงษาสนธิ์ |
Q1 |
นานาชาติ |
ชื่อวารสาร
-
AIMS Mathematics
|
| 23 |
Type 2 degenerate modified poly-Bernoulli polynomials arising from the degenerate poly-exponential functions |
Type 2 degenerate modified poly-Bernoulli polynomials arising from the degenerate poly-exponential functions |
We present a new type of degenerate poly-Bernoulli polynomials and numbers by modifying the polyexponential function in terms of the degenerate exponential functions and degenerate logarithm functions. Also, we introduce a new variation of the degenerate unipoly-Bernoulli polynomials by the similar modification. Based on these polynomials, we investigate some properties, new identities, and their relations to the known special functions and numbers such as the degenerate type 2-Bernoulli polynomials, the type 2 degenerate Euler polynomials, the degenerate Bernoulli polynomials and numbers, the degenerate Stirling numbers of the first kind, and λ-falling factorial sequence. In addition, we compute some of the proposed polynomials and present their zeros and behaviors for different variables in specific cases. |
พัชรี วงษาสนธิ์ |
Q1 |
นานาชาติ |
ชื่อวารสาร
-
AIMS Mathematics
|
| 24 |
Applicability of Representations of F4 to Solutions of a System of PDEs |
Applicability of Representations of F4 to Solutions of a System of PDEs |
This paper is concerned with the applications of representations of the Lie group of class F4 to PDEs. A realization of all irreducible finite-dimensional representations of F4 is found and their application to a study of solutions of some systems of partial differential equations is given. © 2022 by TJM. All rights reserved. |
ศราวุธ แสนการุณ |
Q4 |
นานาชาติ |
|
| 25 |
0 |
0 |
Introduction. The aim of this research is to investigate changes in Thai educators’ attitudes towards their understanding of Asperger’s Syndrome before and after a teacher-training session. Currently, opportunities for professional training regarding Asperger’s Syndrome are very scarce in Thai educational communities. Educators may not be able to provide optimum education and guidance for their students with Asperger’s Syndrome. Meanwhile, these students’ learning outcomes are significantly affected by their educators lacking knowledge of evidence-based intervention methods. Therefore, based on a needs assessment, a teacher-training session was developed to minimize the gaps in pedagogical knowledge and practice. Materials and Methods. A quasi-experimental, embedded mixed-methods design was used to obtain data. This study employed a one-group, pre-test/post-test design, as there were no control groups involved due to the novel learning subject matter. The limitations of the current study – its structure and participant recruitment – were identified and discussed. An availability sampling method was used for this study, resulting in the recruitment of 12 in-service teachers and 32 pre-service teachers from the northeastern region of Thailand. Questionnaires and interviews were used as measurement tools to comprehensively capture participants’ learning experiences. For the statistical analysis, the paired sample t-test (alpha = .05) was used. Meanwhile, for the descriptive analysis, the deductive approach was used. Results. Our results corroborate our sequential hypotheses regarding a teacher-training session and educators’ perceived levels of understanding of Asperger’s Syndrome. The training session was developed with a hypothesis that teachers needed educational opportunities to acquire proper knowledge of Asperger’s Syndrome, so that their students could be fully benefited from the pedagogy. As a result of attending the session, a statistically significant increase in correct response rates was indicated. Indeed, this increase in knowledge fulfilled the second hypothesis that by having proper knowledge of Asperger’s Syndrome, teachers’ professional reflexivity can be improved. Discussion and Conclusion. The outcomes of this study indicate that a teacher-training session has played a crucial role in cultivating Thai educators’ understanding of Asperger’s Syndrome. The outcomes present an interesting correlation between teachers’ knowledge acquisition and their increased professional and personal reflections. Simultaneously, the findings of this study suggest the potential benefits of improving research methodology, including an employment of randomized control trial, a larger sample size, and diversity within the sample population. |
ณัฏฐ์ ดิษเจริญ |
Q2 |
นานาชาติ |
ชื่อวารสาร
-
Integration of Education
|
| 26 |
Artificial Intelligence Model of the User Patterns and Behaviors Analysis on Social Media to Become Customers in Smart Marketing |
Artificial Intelligence Model of the User Patterns and Behaviors Analysis on Social Media to Become Customers in Smart Marketing |
This research aims to analyze the patterns and behavior of social media users on Facebook Pages that sell products online and develop mobile applications to predict whether such users are likely to become customers. The data or actions taken by Facebook users are collected for sentiment analysis of texts and emotional analysis of emojis. Then, the feature selection technique was applied by Gain Ratio, Chi-Square, and Correlation-based Feature Selection. The developed model is based on machine learning techniques, including Decision Tree, Random Forest, Naive Bayes, Support Vector Machine, and MultiLayer Perceptron Neural Network. The result has shown that the model developed by applying the Multi-Layer Perceptron Neural Network and Correlation-based Feature Selection is the highest model performance compared to other models in this work. This model has an efficiency of 89.80% accuracy while having a Mean Absolute Error of 0.102. |
วงกต ศรีอุไร |
Q4 |
นานาชาติ |
|
| 27 |
Using packaging material problems to promote student awareness about the role of mathematics in STEM |
Using packaging material problems to promote student awareness about the role of mathematics in STEM |
STEM learning systems in which the roles of all subjects are unequal, may have a detrimental impact on student learning in neglected subject roles. Therefore, STEM learning packages should have sub-activities that assist students to see the interdependence of all disciplines, especially in mathematics. The nature of the content makes it quite difficult to link it to the mission of STEM. As a result, both teachers and learners are not explicitly aware of the role of mathematics in STEM. Mathematics should not be seen as a simple component in the design of STEM activities, but rather as a vital and necessary aspect. STEM activities based on packaging material problems were developed in this study. The goal is to promote student awareness of the role of mathematics in STEM activities. Seventy-one students, aged 16 and 17 years old, participated in a one-day STEM camp. When the activities were completed, it was found that assessment of student awareness of the role of mathematics in STEM activities was positive. Moreover, teamwork was assessed by groupmates. The evaluation results showed that their behavior was satisfactory. These results indicate that the developed activities are useful for STEM learning in classroom contexts that lack clear tasks reflecting the role of mathematics. Interested instructors can integrate this activity into one sub activity in their own classroom STEM learning packages as appropriate. |
สุพจน์ สีบุตร |
Q1 |
นานาชาติ |
|
| 28 |
Numerical Procedure for Fractional HBV Infection with Impact of Antibody Immune |
Numerical Procedure for Fractional HBV Infection with Impact of Antibody Immune |
The current investigations are presented to solve the fractional order HBV differential infection system (FO-HBV-DIS) with the response of antibody immune using the optimization based stochastic schemes of the Levenberg-Marquardt backpropagation (LMB) neural networks (NNs), i.e., LMBNNs. The FO-HBV-DIS with the response of antibody immune is categorized into five dynamics, healthy hepatocytes (H), capsids (D), infected hepatocytes (I), free virus (V) and antibodies (W). The investigations for three different FO variants have been tested numerically to solve the nonlinear FO-HBV-DIS. The data magnitudes are implemented 75% for training, 10% for certification and 15% for testing to solve the FO-HBV-DIS with the response of antibody immune. The numerical observations are achieved using the stochastic LMBNNs procedures for soling the FO-HBV-DIS with the response of antibody immune and comparison of the results is presented through the database Adams-Bashforth-Moulton approach. To authenticate the validity, competence, consistency, capability and exactness of the LMBNNs, the numerical presentations using the mean square error (MSE), error histograms (EHs), state transitions (STs), correlation and regression are accomplished. © 2023 Tech Science Press. All rights reserved. |
ศักดิ์ดา น้อยนาง |
Q1 |
นานาชาติ |
|
| 29 |
A Novel Two-Step Inertial Viscosity Algorithm for Bilevel Optimization Problems Applied to Image Recovery |
A Novel Two-Step Inertial Viscosity Algorithm for Bilevel Optimization Problems Applied to Image Recovery |
This paper introduces a novel two-step inertial algorithm for locating a common fixed point of a countable family of nonexpansive mappings. We establish strong convergence properties of the proposed method under mild conditions and employ it to solve convex bilevel optimization problems. The method is further applied to the image recovery problem. Our numerical experiments show that the proposed method achieves faster convergence than other related methods in the literature. |
รตนกร วัฒนทวีกุล |
Q1 |
นานาชาติ |
|
| 30 |
A Novel Inertial Viscosity Algorithm for Bilevel Optimization Problems Applied to Classification Problems |
A Novel Inertial Viscosity Algorithm for Bilevel Optimization Problems Applied to Classification Problems |
Fixed-point theory plays many important roles in real-world problems, such as image processing, classification problem, etc. This paper introduces and analyzes a new, accelerated common-fixed-point algorithm using the viscosity approximation method and then employs it to solve convex bilevel optimization problems. The proposed method was applied to data classification with the Diabetes, Heart Disease UCI and Iris datasets. According to the data classification experiment results, the proposed algorithm outperformed the others in the literature. |
รตนกร วัฒนทวีกุล |
Q1 |
นานาชาติ |
|
| 31 |
Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques |
Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques |
During the COVID-19 Pandemic, many universities in Thailand were mostly locked down and classrooms were also transformed into a fully online format. It was challenging for teachers to manage online learning and especially to track student behavior since the teacher could not observe and notify students. To alleviate this problem, one solution that has become increasingly important is the prediction of student performance based on their log data. This study, therefore, aims to analyze student behavior data by applying Predictive Analytics through Moodle Log for approximately 54,803 events. Six Machine Learning Classifiers (Neural Network, Random Forest, Decision Tree, Logistic Regression, Linear Regression, and Support Vector Machine) were applied to predict student performance. Further, we attained a comparison of the effectiveness of early prediction for four stages at 25%, 50%, 75%, and 100% of the course. The prediction models could guide future studies, motivate self-preparation and reduce dropout rates. In the experiment, the model with 5-fold cross-validation was evaluated. Results indicated that the Decision Tree performed best at 81.10% upon course completion. Meanwhile, the SVM had the best result at 86.90% at the first stage, at 25% of the course, and Linear Regression performed with the best efficiency at the middle stages at 70.80%, and 80.20% respectively. The results could be applied to other courses and on a larger e-learning systems log that has similar student activity conditions and this could contribute to more accurate student performance prediction |
ชยาพร แก่นสาร์ |
Q1 |
นานาชาติ |
|
| 32 |
Note on fuzzifying probability density function and its properties |
Note on fuzzifying probability density function and its properties |
This paper applies the concepts of fuzzifying functions to the probability density function of a random variable and introduce a fuzzifying probability to better understand the probability arising from the uncertainties of the probability density function. Using the fuzzifying probability, we derive the fuzzifying expected value and the fuzzifying variance of a random variable with the fuzzifying probability density function. Additionally, we provide examples of a fuzzifying probability density function to validate that the proposed fuzzy concepts generalize crisp expected value and variance in probability theory. |
พัชรี วงษาสนธิ์ |
Q1 |
นานาชาติ |
ชื่อวารสาร
-
AIMS Mathematics
|
| 33 |
Predicting New Student Performances and Identifying important Attributes of Admission
Data Using Machine Learning Techniques with Hyperparameters Tuning |
Predicting New Student Performances and Identifying important Attributes of Admission
Data Using Machine Learning Techniques with Hyperparameters Tuning |
Recently, many global universities have faced high student failure and early dropout rates reflecting on the quality of education. To tackle this problem, forecasting student success as early as possible with machine learning is one of the most important approaches used in modern universities. Thus, this study aims to analyze and compare models for the early prediction of student performance with six machine learning based on Thailand’s education curriculum. A large dataset was collected from the admission scores of 5,919 students during 2011-2021 of 10 programs in the Faculty of Science at Ubon Ratchathani University. The methodology was carried out using Jupyter Notebook, Python 3, and Scikit-Learn to build the models for prediction. To obtain a higher result, we needed not only to find high-performance prediction models, but also to tune hyperparameter configurations consisting of 138 possible different patterns to identify the best-tuned model for each classifier. Furthermore, we investigated significantly important predictors affecting student success for 10 programs in our faculty. In the experiments, the process was divided into two parts: First, we evaluated effective models using a confusion matrix with 10-fold cross-validation. The results showed that random forest (RF) had the highest F1-measure of 86.87%. While predictive models using fine-tuned RF of 10 programs claimed accuracy of about 72% to 93%. Second, we computed the importance of each feature with fine-tuned RF classifiers. The result showed that national test scores (e.g., ONET-English, ONET-Math, ONET-Science, ONET-Social studies, ONET-Thai, and PAT2), entry type, and school grade (e.g., art, English, GPA, health, math, science, and technology) are highly influential features for predicting student success. In summary, these results yield many benefits for other relevant educational institutions to enhance student performance, plan class strategies and undertake decision-making processes. |
ชยาพร แก่นสาร์ |
Q1 |
นานาชาติ |
|
| 34 |
Estimating the Mean of PM2.5 with Missing Data in the Area Around Electricity Generating Authority of Thailand Using the Improved Compromised Imputation Method |
Estimating the Mean of PM2.5 with Missing Data in the Area Around Electricity Generating Authority of Thailand Using the Improved Compromised Imputation Method |
Particulate matter with an aerodynamic diameter of less than 2.5 mm or , is one of the air pollutants that has been found to be at unsafe levels for a number of years in Thailand, leading to public health concerns. In order to lessen the detrimental effects of air pollution, monitoring and analysis of concentration are crucial. Following the study of data from the Pollution Control Department Report in the area around the Electricity Generating Authority of Thailand in January 2019, it was found that there was data missing in the information. It is well-known that missing data can reduce the accuracy of data analysis. To solve the missing data problem, this paper proposes an improved method of compromised imputation and a corresponding resultant estimator to deal with estimating the mean of concentrations in the area. The bias and mean square error of the estimator obtained from the proposed method were derived. The conditions which favor the performance of our estimator over other estimators obtained from the mean, ratio, and compromised imputation methods were obtained using mean square error to apply in the area. The mean of concentrations in this case using the proposed estimator was equal to 47.13 mg/m3, indicating that it did not exceed unsafe levels (£ 50 mg/m3) under certain conditions. In order to support more accurate data analysis that will lead to effective management of air pollution problems in the future, this research proposes a new method that is more effective than the existing methods under missing data problem. |
คณิศา โชติจันทึก |
Q3 |
นานาชาติ |
|
| 35 |
Assessing heart rate and blood pressure estimation from image photoplethysmography using a digital blood pressure meter |
Assessing heart rate and blood pressure estimation from image photoplethysmography using a digital blood pressure meter |
This study presents a non-contact approach to measuring heart rate and blood pressure using an image photoplethysmography (iPPG) signal, and compares the results to those from an oscillometric blood pressure meter. Facial videos of 100 subjects were recorded via a webcam under ambient lighting conditions to extract iPPG signals. The results revealed a strong correlation between the heart rate derived from iPPG and that obtained from an oscillometric blood pressure meter. In addition, a continuous wavelet transform images with a 6-s duration were used as input for a custom convolutional neural network model, providing the most accurate blood pressure estimation. The proposed method received a grade A for diastolic and grade B for systolic blood pressure based on the British Hypertension Society's criteria. It also met the standards set by the Association for the Advancement of Medical Instrumentation. This non-contact framework shows promising potential for efficient screening purposes. |
เกรียงศักดิ์ ตรีประพิณ |
Q1 |
นานาชาติ |
|
| 36 |
Combining GPT and Colab as learning tools for students to explore the numerical solutions of difference equations |
Combining GPT and Colab as learning tools for students to explore the numerical solutions of difference equations |
One of the most important things you can do to improve your mathematical application is to learn how to find numerical solutions. However, it was discovered that classrooms teaching methods that use numerical solutions are largely unable to provide students with the successful experience they should have in finding numerical solutions. Since conceptual and procedural knowledge, as well as the ability to perform computational mathematics, must be understood, simultaneously mastering all three can be difficult for most students. This study investigates combining GPT and Colab as learning tools for students to explore numerical solutions in the context of difference equations. The developed learning process works in tandem with the power of GPT and Colab to provide students with a successful experience in finding numerical solutions to difference equations. The survey results show that students have a high level of self-efficacy in finding numerical solutions to difference equations. This reflects today’s power of innovation, which can be applied in classroom to improve student skills so that they can use the tools to solve problems. |
สุพจน์ สีบุตร |
Q1 |
นานาชาติ |
|
