| Publisher: Mahasarakham Rajabhat University (Total: 4 journals) [Sort by number of followers]
| ||||||||||
|
Journal of Applied Informatics and Technology
Number of Followers: 0  Open Access journalISSN (Print) 2630-094X - ISSN (Online) 2586-8136 Published by Mahasarakham Rajabhat University  [4 journals]
|
- Smart Application for Thai and English Sign Language Translation
Authors: Sahachok Khumwongsa, Wiyada Yawai
Abstract: Currently, deaf people use sign language to communicate, but the general public does not understand sign language very well, which causes misunderstandings. Therefore, the purpose of this research is to enable normal people and deaf people to communicate correctly. This system uses real-time webcam technology and was developed using Google's Mediapipe, which is a tool that uses Machine Learning technology for processing. The developers designed the system to calculate the position of each hand and fingers for each sign, both left and right, and convert them into words. The system has been tested on 68 Thai and English sign language words and can display both text and spoken output with an average accuracy of 95.39%.
PubDate: 2023-09-22
Issue No: Vol. 5, No. 2 (2023)
- Measurement of Word Similarity for Diabetes Question Answering System
Authors: Tanapol Chamnanhan, Ketsara Phetkrachang, Santi Sathiwantana, Pongsagorn Pongsagorn, Chaisit Choosong
Pages: 86 - 99
Abstract: Diabetes is a chronic disease that cannot be cured and is a major problem for the public health of Thailand. The Department of Disease Control predicts that by 2025 there will be more than 7.41 million people in Thailand with diabetes. Continuous self-care for people with diabetes is one method that helps to reduce the incidences of complications arising in already compromised body systems affecting the lives of patients. This research, therefore, presents a measure of the similarity of words in Thai question-answering systems for diabetes by using Cosine, Dice and Jaccard methods to compare the effectiveness of finding answers for the benefit of people who want to know about the initial symptoms of diabetes and self-care for people with diabetes. The preliminary results from the study comparing answer finding efficiency using the question-answer similarity measurement methods found that Cosine was the most effective in finding answers with a precision value of 92.50%, followed by Jaccard and Dice which had precision values of 80.28% and 52.50% respectively.
PubDate: 2023-05-29
Issue No: Vol. 5, No. 2 (2023)
- Classification of MRI Images for Brain Tumor Patient Screening
Authors: Kamonchanok Siphating, Nonthawat Peranam, Weerasak Sawangloke, Anupong Sukprasert
Pages: 100 - 115
Abstract: This research aims to create a model for screening brain tumor patients using MRI imaging data from www.kaggle.com. The data was gathered by Chakrabarty (2021) with a total of 253 images. The data was analyzed using the cross-industry standard process for data mining, then the performances of the classification models were compared. The results showed that random forest technique gave the best result for predicting the likelihood of brain tumors, with an accuracy of 76.31%. The F-measure was 73.48% with a sensitivity of 70.14% and a specificity of 82.69%. The data analysis results could be utilized to develop an information system for future patient screenings for brain tumors.
PubDate: 2023-05-29
Issue No: Vol. 5, No. 2 (2023)
- Thai Silk Patterns Classification with Deep Neural Networks
Authors: Nakharin Ingo, Budsarathip Phatichaikiart, Sakpod Tongleamnak, Thanaphon Tangchoopong
Pages: 116 - 129
Abstract: The art of silk weaving has been transferred through generations as part of folk wisdom. Every locality has its distinct silk pattern design. Expertise and familiarity with silk are necessary for the classification of silk patterns. Therefore, only a few experts can recognize the silk's pattern. This study aims to implement a system for classifying silk patterns using image processing technology to help identify silk patterns from images. This research collected silk pattern data from the Chonnabot district, Khon Kaen Province. We selected 15 silk patterns and collected a total of 2,156 images. We examined two convolutional neural networks (CNNs), which differed in feature extraction and regularization via the dropout technique. The experimental results showed that CNN model 1 achieved an F1-score of 0.62. The CNN model 2, in which feature extraction using the pre-trained model was added to the CNN model 2, achieved an F1-score of 0.92, which can assist in resolving the confusion in silk pattern classification.
PubDate: 2023-05-29
Issue No: Vol. 5, No. 2 (2023)
- Customer Data-Driven E-Marketing Strategy on Social Media in Health and
Beauty Supplements
Authors: Nitiwat Sutticharoen, Perapat Sagiem-ngam, Phennapa Joomponpong
Pages: 130 - 144
Abstract: The objective of this research is to collect customer data and conduct in-depth customer data analysis for use in planning a digital marketing strategy for health and beauty supplement products on social media platforms. The research process includes: 1) Questioning by entrepreneurs related to electronic marketing strategy and data-driven initiatives. 2) Data collection in tabular format, capturing customer information who ordered products through social media between January and July 2022, with a total of 223 individuals and 409 viewing channels. 3) The data analysis is presented in tabular format, showing as totals and percentages, and the data is displayed as a Pivot Table. 4) Deep analysis summary data, by taking data obtained from data analysis and creating it into a Pivot Chart and presenting it in a dashboard format, will result in deep customer summary data. 5) Applying the data to formulate an electronic marketing strategy that aligned with customer needs and digital marketing trends, including video marketing and the data-driven strategy which involves data storage and in-depth analysis of existing customer data in line with future data analysis trends such as an automatic data analysis system. The increased analysis allows entrepreneurs to utilize data for planning, reach target groups, and create value for their business.
PubDate: 2023-05-29
Issue No: Vol. 5, No. 2 (2023)
- Integrating Augmented Reality and Geographic Information Technology to
Promote Tourist Attractions in Hua-Hin District, Prachuap Khiri Khan
Province
Authors: Aungkana Jattamart, Parantiya Plangdecha, Tanchanok Sawatpakdee, Sudyord Pungpang, Achaporn Kwangsawad
Pages: 145 - 164
Abstract: The pandemic of COVID-19 has directly affected the tourism industry. Moreover, tourists now prefer to plan their own trips and travel independently by searching for information online. Consequently, the tourism industry has adapted by employing technology to attract tourists and increase revenue. The objectives of this research were 1) to develop public relations media for Hua-Hin tourist attractions using augmented reality technology in conjunction with geographic information technology and 2) to assess the acceptance of public relations media use. V-director was used to develop augmented reality (AR) media. ArcGIS Online was used to develop geographic information (GIS) technology tools. Then the online questionnaires were used to evaluate the acceptance of developed media usage. The sample group for assessing the acceptance of public relations media usage consists of 402 internet users. The results demonstrated that 1) users can retrieve location information through public relations media displayed as AR videos and can also search travel routes to tourist attractions using GIS tools and 2) The assessment results of user acceptance indicate that the experiential aspect of travel has the highest average score (= 4.59).
PubDate: 2023-05-29
Issue No: Vol. 5, No. 2 (2023)
- Information system for Online Product Management for the Products of Toei
Panan Basketry Community Enterprise, Mae Thom Subdistrict, Bang Klam
District, Songkhla Province
Authors: Ketsara Phetkrachang, Auntika Thipjumnong, Monthana Kongkaew, Waraporn Laohasamphantaporn
Pages: 165 - 177
Abstract: This research is a study on the development of an information system for managing online products for Toei Panan Basketry Community Enterprise, Mae Thom Sub-district, Bang Klam District, Songkhla Province. The objective is to collect and consolidate market operation data of products in electronic format, representing various activities within the community resulting from the production and distribution of these products. The objectives were to: 1) develop an information system for online product management 2) evaluate the efficiency of the system. The research methods consisted of 1) studying and collecting fundamental data about the group 2) developing the information system using the SDLC development cycle 3) evaluating the satisfaction and efficiency of the system. The sample group in this research was Toei Panan Basketry Community Enterprise, Mae Thom Subdistrict, Bang Klam District, Songkhla Province. The preliminary results show that the system can be used to provide real benefits, and the results of the system's quality assessment by experts support this. The average result was at a very good level, with a mean of 4.64 and a standard deviation (S.D.) of 0.57. Moreover, user satisfaction with the system is also at a very good level with an average score of 4.53 and a standard deviation of 0.53.
PubDate: 2023-07-03
Issue No: Vol. 5, No. 2 (2023)
