Pokpong Songmuang

• Ph.D. (Information Systems)
• Professor (Assistant) at Thammasat University

Over the years, online education has become an alternative mode of teaching and learning. It has become another venue for education and instruction. However, many students have limited preparation for online education. This work thus proposes a recommendation system to predict online education adaptability. The system is designed to recommend solut...

Supervised deep learning techniques are state-of-the-art methods in satellite image analysis; however, this technique requires a large, labeled dataset. The acquisition of such datasets is expensive in terms of both manpower and resources. Conversely, there is an abundance of raw satellite images, available for both commercial and academic purposes...

This paper presents the generation method for an explainable model based on the given information of a black box model using a concept of knowledge transfer to synthesize a dataset. The proposed method applies with GAN and Bee algorithm (BA) for data synthesis technique to synthesize a dataset by considering loss value in a knowledge transferring p...

การควบคุมทางสังคมเป็นหนึ่งในกลไกที่สำคัญที่นำมาสู่การสร้างความเป็นระบบของสังคม เพื่อให้ประชาชนสามารถอยู่ร่วมได้อย่างสงบสุข ระบบเครดิตทางสังคมเป็นหนึ่งในรูปธรรมของการควบคุมทางสังคมที่รัฐสร้างขึ้นเพื่อให้พลเมืองเกิดการควบคุมการแสดงพฤติกรรมของตนเอง การดำเนินระบบเครดิตทางสังคมดำเนินไปควบคู่กับกระบวนการให้รางวัลและลงโทษ เพื่อให้สมาชิกในสังคมเกิดความตะหน...

Existing missing value imputation methods focused on imputing the data regarding actual values towards a completion of datasets as an input for machine learning tasks. This work proposes an imputation of missing values towards improvement of accuracy performance for classification. The proposed method was based on bee algorithm and the use of k-nea...

This paper presents the usage of semantic graphs as a knowledge resource for semantic comparison between queries and document contents. The semantic graph is generated by the concept of Natural Language Processing. The processes in semantic graph generation are started from document preprocessing. These preprocessing steps are word tokenization, st...

This research addresses the global prevalence of people with hearing disabilities, recognizing the increasing numbers within this demographic. The communication challenges encountered by these individuals drive the development and evaluation of a language translation model. The primary goal is to design a model specifically tailored for translating...

งานวิจัยนี้มีวัตถุประสงค์เพื่อศึกษาความต้องการและทัศนคติของคนไทยต่อการจัดการภัยพิบัติในแต่ละเหตุการณ์ของรัฐบาลไทย จากทวิตเตอร์เป็นจำนวน 3 แฮชแท็ก ได้แก่ สารเคมีรั่ว โรงงานกิ่งแก้วไฟไหม้ และ น้ำท่วมอุบล จึงได้นำความรู้เรื่อง Sentiment Analysis มาประยุกต์ใช้ ซึ่งข้อมูลที่ได้จะนำไปใช้มี 2 ชุดข้อมูล คือ ชุดข้อมูลทั้งหมด และชุดข้อมูลที่จะนำไปทำแบ่งกลุ่ม...

Coronavirus disease (COVID-19) is a major pandemic disease that has already infected millions of people worldwide and affects many aspects, especially public health. There are many clinical techniques for the diagnosis of this disease, such as RT-PCR and CT-Scan. X-ray image is one of the important techniques for medical diagnosis and easily access...

การที่คอมพิวเตอร์สามารถรู้จำการกระทำของมนุษย์เกิดจากการที่โมเดลสามารถทำนายได้ว่า มนุษย์กำลังกระทำการกระทำอะไรอยู่ โดยใช้ข้อมูลวิดีโอของสถานะการกระทำในปัจจุบัน การรู้จำการกระทำของมนุษย์สามารถนำไปประยุกต์ได้หลายด้านเช่น ความปลอดภัย ความบันเทิง การอำนวยความสะดวก ซึ่งงานวิจัยในสาขานี้มีการเปลี่ยนแปลงรวดเร็วมาก ดังนั้น ในงานสำรวจนี้รวบรวมงานวิจัยการรู้จ...

Motivation: Existing missing value imputation methods focused on imputing the data regarding actual values. These mainly assisted towards a completion of datasets as an input for machine learning tasks. Gene expression dataset was one of expensive datasets that usually contains missing values from insufficient resolution and dust contaminants. As g...

การที่คอมพิวเตอร์สามารถรู้จำการกระทำของมนุษย์เกิดจากการที่โมเดลสามารถทำนายได้ว่า มนุษย์กำลังกระทำการกระทำอะไรอยู่ โดยใช้ข้อมูลวิดีโอของสถานะการกระทำในปัจจุบัน การรู้จำการกระทำของมนุษย์สามารถนำไปประยุกต์ได้หลายด้านเช่น ความปลอดภัย ความบันเทิง การอำนวยความสะดวก ซึ่งงานวิจัยในสาขานี้มีการเปลี่ยนแปลงรวดเร็วมาก ดังนั้น ในงานสำรวจนี้รวบรวมงานวิจัยการรู้จ...

Supervised deep neural networks are the-state-of-the-art for many tasks in the remote sensing domain, against the fact that such techniques require the dataset consisting of pairs of input and label, which are rare and expensive to collect in term of both manpower and resources. On the other hand, there are abundance of raw satellite images availab...

Diseases like common cold, influenza, dengue fever, respiratory syncytial virus (RSV), and hand-foot-and-mouth disease (HFMD) are very common in children because they have low immunity and cannot avoid the risk of contracting the disease. In addition, all of these five diseases exhibit similar types of symptoms. Sometimes, it is difficult to identi...

The purposes of the research were: 1) to develop a keyword suggestion feature for searching Thai document based on dictionary and ontology keyword suggestions. 2) to compare the effectiveness of keyword suggestions for searching Thai documents. 3) to study keyword suggestion feature results for searching Thai documents from users in a real trial. T...

The current methods for missing link prediction in social networks focus on using data from overlapping users from two social network sources to recommend links between unconnected users. To improve prediction of the missing link, this paper presents the use of information from non-overlapping users as additional features in training a prediction m...

Human interaction with chicken can be traced back to prehistorical period. These interactions range from hunting to domestication for consumption. With high demand in the present time, indoor chicken farming is the most common method to domesticate chicken. However, this method requires large amount of labor to harvest large quantity of chicken. He...

The problem of delivery is a general problem of the salesman how to deliver the goods for shortest distance to any location in which more than 1 salesman is allowed. This problem is called Multi-Traveling Salesman Problem. And our research will compare performance between Genetic Algorithm and Bee Algorithm. We develop program for solution to find...

Generally, voice activity detection (VAD) commonly uses a silence over 100-ms as an endpoint of speech. Previously, the short pause based VAD is proposed to reduce the waiting time of caption result in automatic captioned relay service. This technique reduces the waiting time of caption result well. However, an accuracy of caption result is not mai...

Several researches performed experiments to compare performances of data clustering methods based on nature-inspired algorithms using various data types including text document dataset. According to the results, although Firefly algorithm showed high performance to cluster text document over several nature-inspired algorithms but Bees algorithm had...

The Automatic Captioned Relay Service is crucial for hearing disabilities or hard-of-hearing to communicate with others in real life. This service uses an Automatic Speech Recognition (ASR) to transcribe speech to a caption. If can reduce waiting time from non-streaming speech recognition, the relay service will support more users. In this paper, w...

This paper presents a salary prediction system using a profile of graduated students as a model. A data mining technique is applied to generate a model to predict a salary for individual students who have similar attributes to the training data. In this work, we also made an experiment to compare five data mining techniques including Decision trees...

Educational assessments occasionally require uniform test forms for which each test form comprises a different set of items, but the forms meet equivalent test specifications (i.e., qualities indicated by test information functions based on item response theory). We propose two maximum clique algorithms (MCA) for uniform test form assembly. The pro...

. Educational assessments occasionally require “uniform test forms” for which each test form consists of a different set of items, but the forms meet equivalent test specifications (i.e., qualities indicated by test information functions based on item response theory). We propose two maximum clique algorithms (MCA) for uniform test forms assembly....

This paper proposes methods for designing and analyzing an item bank for constructing multiple equivalent test forms. Several studies proposed methods for designing and analyzing an item bank but most of them were proposed for computerized adaptive testing instead of constructing multiple equivalent test forms. Therefore, we propose the methods bas...

We propose an automatic construction method of multiple equivalent test forms indicated by test information function, and the method reduces the probabilities of selecting redundant items to the same test form. In previous studies, although their methods minimized the different between the test information functions of the constructed test forms, t...

The purpose of this research is to automatically construct multiple equivalent test forms that have equivalent qualities indicated by test information functions based on item response theory. There has been a trade-off in previous studies between the computational costs and the equivalent qualities of test forms. To alleviate this problem, we propo...

This paper proposes a new construction method of multiple test forms that applies a Bees Algorithm and a parallel computation technique to improve the computational costs of the traditional methods.

This paper proposes a new computerized adaptive testing employing a decision tree model, instead of test theories. The attribute variable of the model is examinees' responses to each item and the output variable is examinees' test total scores. Some simulation experiments show better performances of the proposed method compared to the traditional m...

It is known that there are the following problems in distance education for two or more classes. 1) The reaction of the learner in the remote place is not understood easily. 2) It sometimes confuses the teacher which class he/she should observe. 3) It is difficult to realize an interactive lecture. This paper proposes a response analyzer system usi...

We utilized e-Learning using example data from special support education stored in a web database as e-Learning contents. The e-Learning was conducted with teachers from various educational institutes: from primary schools to universities, in addition to special support schools. Through a collective problem solving process we were able to collect i...

This paper proposes an e-testing construction support system (eTCSS) with the prediction tools for the constructed test. This paper performs some comparison experiments to find the best predictive performances models for the predictive response-time distribution and the predictive response-time distribution. Furthermore, the amount of test informat...

In the context of e-learning contents, if we take an approach based on the "Dual Channel" model, which is well known as a processing model for human perceptual judgments, cognitive resources can be used most effectively by methods that synchronize narrations with images and video contents. In general, however, the learner must search for a visual f...

Analysis of collaborative e-test construction identified the number of test-authors as the most important factor in test validity, while test reliability depends more on participation of an expert. Based on these findings, a collaborative e-test construction system was developed that uses predicted response-time and score distributions to improve t...

This paper focuses on one of the features of e-testing, which has not been discussed until now, collaborative test construction by several test-authors in distant places. It is well known that collaborative work has many advantages. The main idea of this paper is to apply the unique advantages of collaborative work to e-test construction. The purpo...

This paper focuses on one of the features of e-testing, which has not been discussed until now, called collaborative test construction by several test-authors in distant places. It is well known that collaborative work has many advantages. The main idea of this paper is to improve test qualities by applying the unique advantages of collaborative wo...