JOURNAL OF INFORMATION SCIENCE AND TECHNOLOGY

A Study of Following News from News Agencies on Facebook and Political Preferences

Nattapong Kongaium, Chetneti Srisa-An — Fri, 29 Dec 2023 00:00:00 +0700

The objectives of this research are 1) to study the behavior of receiving media from Thailand’s news agencies on Facebook medium to be able to use in the news agency's public relations planning. 2) To study a relationship between preferences for political parties and news agencies on Facebook. The results showed that most of the respondents were female, aged between 26-43 years old, educated at a bachelor's degree. Have a career in government service/state enterprise and average monthly income between 15,001 - 30,000 baht, having a single status and having 3-4 family members. The news and the main occupation had a statistically significant relationship. In the aspect of the hypothesis, the relationship between news agencies on Facebook. With political party preference was found to have a statistically significant relationship.

3D modeling media in STEAM education on Chinese instructional for secondary student at 10th

Araya Pijaksanaporn , Phum atakuaithung — Fri, 29 Dec 2023 00:00:00 +0700

In this paper, we present the result of the development of learning technique for using 3D model with STEAM Education for learn Chinese. Learners given more on practice and develop skill that engage curiosity and self-learning. We developed a learning system that integration subsistence wish suit to the age and student development wish will fortify student thought process, questioning, searching for reasons and truly understanding answers. By a combination of digital teaching medias and 3D paper crafting for teaching “Telling Time in Modern Chinese” and “Ancient Chinese Language”. It is evaluated with 40 high school students and collect student’s attitude in Chinese language learning. The results showed that the attitude has 0.67-point increase or 4 percentages.

Urban Growth Monitoring in Chanthaburi Using Remote Sensing Data on Google Earth Engine

Kumpee Teeravech, Kanitta Yarak, Tobthong Chancharoen — Fri, 29 Dec 2023 00:00:00 +0700

Google Earth Engine remote sensing data, consisting of 102 images acquired by LANDSAT-5 TM and LANDSAT-8 OLI satellites, were utilized to classify six land use categories using the Random Forest algorithm. The primary objective was to analyze land use patterns spanning a temporal span of three decades. To achieve this, we deployed machine learning techniques, specifically the Random Forest algorithm, with the aim of examining temporal changes and identifying patterns related to urban expansion. Our analysis revealed that between 1992 and 2012, herbaceous and field crops were the predominant land use categories, with areas of 3,404.96 sq.km., 2,596.02 sq.km., 2,404.79 sq.km., 2,604.32 sq.km., and 2,623.44 sq.km. at five-year intervals. However, a significant shift occurred in 2017 and 2022 when land use transitioned toward perennial fruit and woody crops, becoming the top-ranking land use category with areas of 2,695.83 sq.km. and 2,516.83 sq.km. This transformation was accompanied by a simultaneous increase in urban expansion, indicating a noticeable departure from the cultivation of herbaceous and field crops. Moreover, there was a noticeable decline in the extent of land allocated to perennial fruit crops. Projections based on the CA-Markov model predict a sustained trend of urban expansion, with the urban area and infrastructure expected to reach 115.15 sq.km. and 126.02 sq.km. by 2027 and 2032, respectively.

A Study of Machine Learning for Crude Palm Oil Price Prediction

Kanya Siripirom, Datchakorn Tancharoen — Fri, 29 Dec 2023 00:00:00 +0700

This paper focuses on the prediction of Crude Palm Oil prices in Thailand and find the best model for price prediction. Accurate price forecasting is essential for stakeholders in the palm oil industry to make informed decisions and manage risks effectively. In this comparative study between the Baseline Model, Recurrent Neural Network-Long Short-Term Memory, and the Classic models. The Classic model are Regression Model, Exponential Smoothing, Random Forest, LightGBM Model, and Theta Method. The testing will be conducted by comparing performance of models for the crude palm oil price prediction using time series and this is only one factor in this experiment. For the evaluation using the Mean Absolute Percentage Error (MAPE) metric to measure the percentage deviation between the projected and actual prices. It provides insights into the performance of the model. This research found that the baseline model has the lowest MAPE value is 0.08128. Therefore, the Baseline model provides the best accuracy for forecasting crude palm oil prices in Thailand.

Interactive Media for Cognitive Skill Improvement using a Visual Novel Game

Fri, 29 Dec 2023 00:00:00 +0700

The objective of the research is to create the "EDIHI" visual novel game in order to improve cognitive skills. In order to develop creativity and specific problem-solving skills in digital multimedia arts technology for first-year students, the 30 participants were split into two groups: the users of the electronic book medium EDIHI and the users of the game. The qualitative evaluation of visual novel games by experts is divided into five aspects, namely: 1) Game performance; 2) Game effectiveness; 3) Game flexibility; 4) Game presentation; and 5) Game content. The research found that qualitative evaluation of visual novel games by experts has a mean of 4.48 and a standard deviation of 0.51, quality is highest level. According to research studies, users of the visual novel game EDIHI reported higher perceived levels of developing creativity and problem-solving abilities on the fly than users of the electronic book media titled EDIHI at the statistical significance level of 0.05 in all aspects.

Flight Simulator Program in Secondary Surveillance for Air Defense Training

Ponlawat Khamlae, Worawat Choensawat, Kingkarn Sookhanaphibarn — Fri, 29 Dec 2023 00:00:00 +0700

This article presents a program for simulating aircraft in radar airspace for air defense training. The program is specifically designed for close-range and medium-range radar systems, which are crucial in training personnel to detect radar signals without the need for actual aircraft flights. The simulation program can replicate various scenarios, including training exercises with multiple radar systems and realistic situations with a dense number of aircraft. The article introduces an innovation that utilizes the simulation program, generating synthetic radar data from real data collected by FlightRadar24. The program features include: 1) simulating real data collected from FlightRadar24, 2) simulating data with noise synthesis techniques applied to actual data, and 3) generating diverse data using individual flight synthesis and air traffic density synthesis techniques. Experimental results demonstrate that the simulation program can be effectively utilized in real air defense systems.

Image Classification of Tomato Leaf Diseases using Convolutional Neural Network

Nutchanun Chinpanthana — Fri, 29 Dec 2023 00:00:00 +0700

Tomato is one of the most important cultivated vegetable plants in the world. The continuous expanded production and consumption of tomato has grown quickly. It is considered a mainstay of many economic country. Tomato crops can be damage due to various kinds of diseases that are recently discovery of diagnosis errors or not prevented and controlled timely. The problems faced by farmers are typically unnoticed and lack knowledge in crop production. For developing an early treatment process, the identify infections of plant diseases in a rapid can help to reduce huge economical suffering. In agricultural practices is detect of disease manually on crops which is very complex, time-consuming and more tedious tasks. This paper discussing the technique base on digital image processing, which employs the convolutional neural network deep learning model to classify tomato leaf diseases. The dataset is classified into 10 classes: bacterial leaf spot, early blight, late blight, leaf mold, septoria leaf spot, two-spotted spider mite, target spot, cucumber mosaic virus, yellow leaf curl virus and fresh leaf. The approach is composed of four main phases: (1) data preprocessing, (2) generated model convolutional neural network, and (3) model evaluation and (4) deployment. The experimental results indicated that deep learning with convolutional neural network technique has the highest effectiveness in recognizing tomato leaf diseases with the total average accuracy at 87.96% at learning rate 0.001 for 100 epochs.

Design and Simulation of Chessboard Coding Wave Artifacts

Tanatorn Tantipiriyakul , Komsan Kanjanasit — Fri, 29 Dec 2023 00:00:00 +0700

This paper presents a numerical simulation of a binary chessboard-coding artifact in the designs of wave objects for upcoming smart communication in a centimeter-wave range. The binary-coding artificial structures can be composed of a mixture of two types of unit cells with the digital states of “0” and “1” elements in a two-dimensional (2D) structure. The binary characters are essential to a unity magnitude of a reflection type with the dependence of an opposite phase response at 0 and 180. The proposed binary coding configuration relies on utilizing an artificial magnetic conductor (AMC) which is formed by a patch-based array over a perfect ground surface with a dielectric slab. The scattering characteristic is illustrated at the operating frequency of 10 GHz. The antenna device as a wave object is designed using the binary chessboard-coding artifact with a function of wave radiation. With a simulation technique, numerical analysis provides an understanding of the electromagnetic (EM) effect of binary-coding unit cells and antenna designs. The results of a computational process can identify the potential properties of the chessboard-coding artifact.

The Enterprise Architecture Analysis: A Case Study of The Division of Finance, University of Phayao

Pichai Chaikul, Kaewarin Jandum, Sitthidet Vachirasricirikul — Fri, 29 Dec 2023 00:00:00 +0700

Division of finance, University of Phayao is an agency that provides the financial and fiscal supports by establishing the financial and accounting policies, as well as, preparing a database and the financial reports of the university so that the management is efficient and also it responds to the change in the future. The purpose of this research is to analyze and determine the planning and operation frameworks according to the organizational architecture framework of the division of finance, University of Phayao. By using the TOGAF architecture framework, it can divide the analysis into 4 parts and also it can design an enterprise blueprint in order to see the overall picture of the organization and also it can manage systematically. In addition, it can be used in the supporting and decision-making of executives and also it can be utilized for assessing the satisfaction of the division of finance, University of Phayao. Here, the studied target groups consisted of the accounting finance and supplies network groups in University of Phayao, are 41 people. In satisfaction assessment, for the statistic used in the analysis, it is the mean and the standard deviation. For the evaluation results, it is found that the overall satisfaction is in a high level that the mean value is 4.22 and the standard deviation value is 0.77.