KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 13

Some of the metrics are blocked by your
consent settings
Prediction of Water Quality Index (WQI) Using Machine Learning
(2025-01-01)
Kularbphettong, Kunyanuth
;
Raksuntorn, Nareenart
;
Boonseng, Chongrag
The purpose of this project is to assess Water Quality Index (WQI) by using five machine learning techniques including the Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DF), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost). In this case, we are using Thailand as a base country for assessing water quality of the rivers and canals. The data set was collected from Bangkok Metropolitan Authority of Thailand during the period January 2018 to January 2021. The data set included 43,776 records and each record comprised 12 quantitative measurements related to water quality. Hence, they were used as feature inputs of the assessment model; for instance, pH, DO (Dissolved Oxygen), BOD (Biochemical Oxygen Demand), TP (Total Phosphorus), TCB (Total Coloniform Bacteria), FCB (Fecal Coloniform Bacteria), NO3-N (Nitrogen-Nitrogen), No2-N (Nitrogen-Suspended Solid), NH3-N (Ammonia-Nitrogen), TS (Total Solid), and Total Dissolved Solid (TDS). During the phase of preprocessing K-Nearest Neighbors (KNN) and Random Forest were employed to handle missing data and detecting outliers. KNN imputation was applied to address missing values, while Random Forest was implemented to eliminate outliers, so generating the dataset appropriate for model training. The effectiveness of each machine learning model was assessed employing four principal metrics: accuracy, precision, recall, and F1 score. The findings revealed that all five methodologies excelled in predicting WQI; however, the XGBoost model surpassed the others, attaining the highest values across all metrics, including an accuracy of 91%.
Some of the metrics are blocked by your
consent settings
Enhancing Student’s Learning by Integrating the Concept of Project-Based and Challenge-Based Learning
(2025-01-01)
Kularbphettong, Kunyanuth
;
Raksuntorn, Nareenart
;
Roonrakwit, Pattarapan
;
Boonseng, Chongrag
This study aims to enhance student learning in the introductory data science course by combining Project-Based and Challenge-Based Learning methodologies. The goal is to improve student performance, engagement, and comprehend of data science subjects through research and development. By integrating challenge-based learning (CBL) and project-based learning (PBL) into a cohesive teaching approach, the benefits of both approaches are employed to improve the learning experience for students. This methodology facilitates in-depth comprehension, critical reasoning, and practical application of data science skills, preparing students for academic success and real-world obstacles. The research sample comprised 56 third-year undergraduates from the Computer Science department, selected using a purposive sampling method. Data analysis involves the utilization of several statistical techniques such as the t-test, analysis of covariance (ANCOVA), mean, standard deviation, and other relevant statistics. The findings indicated that students who utilized a blend of Project-Based and Challenge-Based Learning methods had a notable increase in academic performance post-learning, as compared to their pre-learning performance, with statistical significance. Firstly, students at the 05 level are more likely to express their satisfaction with the course of study. This is primarily because the course incorporates problem-based learning (PBL) and case-based learning (CBL), which are both engaging and practical teaching methods. Furthermore, this implies that improving student achievement in the data science course is an effective use of the integrated teaching methodology.
Some of the metrics are blocked by your
consent settings
Sentiment analysis of the awareness of environmental sustainability
(2024-01-01)
Kularbphettong, Kunyanuth
;
Roonrakwit, Pattarapan
;
Boonseng, Chongrag
This study examines the sentiment analysis of awareness of environmental sustainability. Environmental sustainability is the responsible management and utilization of Earth's natural resources to meet the needs of the present generation and ensure that future generations will access those resources. The awareness of environmental sustainability has been growing globally as people, businesses, and governments recognize the importance of preserving the planet for current and future generations. Sentiment analysis of environmental sustainability involves evaluating opinions, attitudes, and emotions expressed in texts related to environmental sustainability, and analyzing sentiment can provide insights into public perception, awareness, and engagement with environmental issues. This exploratory study's primary goal is to conduct social media opinion mining in the context of Thai people's environmental sustainability. The paper presented how to build a model of sentiment analysis with linguistic analysis, including data preprocessing steps, feature extraction, and model constructions. The techniques used in this research include Logistic Regression, Random Forests, Support Vector Machine, Word Segmentation and Bag of Words. The result shows that the model is able to categorize sentiment analysis opinions in the sustainability context primarily in positive terms. The positive sentiments suggest a sustained, long-term shift in awareness, or they might be influenced by specific events or trends. However, positive sentiment analysis results are expressed towards environmental sustainability initiatives, such as renewable energy projects, waste reduction efforts, or conservation programs. Moreover, public awareness plays a crucial role in influencing individual behavior, corporate practices, and government policies towards a more sustainable and environmentally conscious future.
Some of the metrics are blocked by your
consent settings
Prediction of CO2 emissions using machine learning
(2024-01-01)
Bussaban, Kanyarat
;
Kularbphettong, Kunyanuth
;
Raksuntorn, Nareenart
;
Boonseng, Chongrag
Carbon dioxide (CO<inf>2</inf>) contributes significantly to climate change as a greenhouse gas. The Earth's atmosphere is naturally kept warm enough to support life by greenhouse gases which trap heat in the atmosphere. However, human activity has significantly increased the amount of CO2 in the atmosphere because of deforestation and the use of fossil fuels. One of the key concerns with human evolution that fuels global climate change is carbon dioxide (CO<inf>2</inf>). It is released as fuels burn and as a result, people worldwide are gradually becoming more conscious of environmental issues. Effective policy formulation requires an investigation of the factors influencing CO<inf>2</inf> emissions, yet tiny datasets and traditional research methodologies have hampered prior investigations. This research uses three prediction models to estimate CO<inf>2</inf> trapping efficiency among CO<inf>2</inf> emissions, energy use and GDP: Multiple Linear Regression (MLR), Support Vector Machine (SVM) and Random Forest (RF). The machine learning (ML) techniques used in this work have demonstrated strong performance with multiple linear regressions, support vector machines and random forest models with mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE). The investigation has proposed a technique for approximating CO<inf>2</inf> emissions and the results indicate that Support Vector Machine (SVM) can attain the highest degree of precision. The outcome could be a useful model for the decision support system to enhance an appropriate course of action for reducing CO<inf>2</inf> emissions worldwide.
Some of the metrics are blocked by your
consent settings
The Monitoring of Electrical System in Stability Using Neural Network by Logistic Regression Model
(2023-12-28)
Boonseng, Chongrag
;
Nilnimitr, Nannam
This project presents a power system stability check using Neuron Networks, where the program analyzes the received data and displays the system stability as a percentage. In this article, we will discuss the Logistic Model used to analyze and predict the results obtained from the program. The parameters used to analyze the power system are voltage, current, power factor, THDv, and THDi, so that users can assess the period of time that the power system has changed and can find a way to do it. maintain the stability of the electrical system.
Some of the metrics are blocked by your
consent settings
Study on the installation of harmonic filter circuits for industrial plants connected to solar energy systems and low harmonic currents
(2023-01-01)
Boonseng, Chongrag
;
Gitnumlapcharoen, Poomipat
;
Boonseng, Rapeepornpat
In industrial systems, solar power systems are used to reduce environmental impact and use less energy from the grid. Solar energy systems have non-linear electrical characteristics that cause harmonic problems. Such problems result in damage to electrical equipment despite the small amount of harmonic current. This paper presents a suitable and simple analytical method to solve this problem by installing a passive filter.
Some of the metrics are blocked by your
consent settings
Water Quality Index (WQI) Prediction Using Machine Learning Algorithms
(2023-01-01)
Kularbphettong, Kunyanuth
;
Waraporn, Phanu
;
Raksuntorn, Nareenart
;
Vivhivanives, Rujijan
;
Sangsuwon, Chanyapat
Water resources used by human activities ranges typically from personal and household, agricultural, industrial, recreational to environmental pursuits. The effects of these water utilizations are actually of great concerns by many due to various threats created by human functions and the nature itself, for instance, climate change, pollution, scarcity, and even conflicts. To mitigate these threats, implementation of water quality management based on recognized standards and guidelines not only will they provide solid framework and benchmark used in relation to the assessment of the water quality but will also enable the identification of corresponding classification indicated by the water quality index (WQI) pertinent and relevant to the surface water dataset. This paper aims at applying selected predictive modeling techniques that are highly optimized for use in semi-automating the work of the water quality classification (WQC) and the water quality index (WQI) that subsequently can be used in assisting the planning, problem-solving and/or decision-making processes. The preliminary results obtained are quite satisfactory as follow: predicting WQI using neural network model (NN) outperforms both the Multiple Linear Regression (MLR) and the Support Vector Machine (SVM) based on a mean absolute error (MAE) lower than the two models and predicting WQC using SVM, and ANN models based on accuracy score with SVM returns a favorable accuracy score higher than two others.
Some of the metrics are blocked by your
consent settings
Electrical Insulation Testing and DGA Analysis for the Diagnosis of Insulation Faults and Failures in 24 MVA Transformers for Distribution Systems
(2020-10-25)
Boonseng, Chongrag
;
Boonseng, Repeepornpat
;
Kularbphettong, Kunyanuth
The distribution transformers in the electrical system collapse result in damage to industrial property, business, and insurance deductibles. So that to reduce the collapse of the system and the expenses for maintenance. The transformer must be inspected by professional and must be regularly checked. This paper represents the investigation and diagnosis of the 24MVA distribution transformer explosion. The explosion cause the transformer oil to flow through the pressure release value violently. To investigate and diagnose the cause of the transformer explosion, electrical parameters are measured to confirm which parts have been damaged. The result of the measurement shows that there is a fault in the HV coil. Then check the transformer oil by Dissolved Gas Analysis (DGA) method, dating back from 2013 to 2019 and after the explosion. The results can confirm that there has been an abnormality since 2014. The inspection of this transformer shows that every year the electrical parameters and transformer oil inspection and DGA analysis according to IEEE Std C57.104-2019 can prevent an explosion.
Some of the metrics are blocked by your
consent settings
The Monitoring of Factory Electrical System in Collapse Using Neural Network Prediction Method
(2020-10-25)
Boonseng, Chongrag
;
Nilnimitr, Nannam
;
Kularbphettong, Kunyanuth
This project presents monitoring of the feasibility of electrical systems by a prediction program created by Neuron Networks which the program can predict the result in the percentage of how strong the power is. In this paper, we will talk about the models used for analysis and the predictive results obtained from the program. When we can predict the strength percentage of the system, it will help the users maintain or prevent the strength of the electrical system lower than the users require. It also helps to reduce the impact of seams on the use of uninterruptible power systems.
Some of the metrics are blocked by your
consent settings
The Low Voltage Isolation Transformer Failure Investigation: Measurements, Analysis and Lessons Learned
(2020-09-01)
Boonseng, Chongrag
;
Boonseng, Rapeepornpat
;
Kularbphettong, Kunyanuth
This paper presents a case study of failure analysis for a 200kVA, 400 V isolation transformer at a semiconductor plant with a start-up with problems faced before permanent damage. The basic requirements of the acceleration of the dynamic transformer to achieve a successful start will be checked In addition, the results of the measurement of the location of the electrical parameters and the separation process are shown to indicate the cause of the error and evidence of the testimony. The results are confirmed by a failure analysis report provided by the manufacturer. This paper also addresses the obstacles that are faced due to the limited error and availability of information and how to solve the problem.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results