KMITL

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

Browse

Search Results

Now showing 1 - 10 of 10

Some of the metrics are blocked by your
consent settings
High dynamic range preprocessing, ParallelAttention Transformer and CoExpression analysis for facial expression recognition
(2025-04-01)
Zhou, Yuntao
;
Kantathanawat, Thiyaporn
;
Tuntiwongwanich, Somkiat
;
Liu, Chunmao
Facial expression recognition (FER) aims to enable computers to automatically detect and recognize human facial expressions, thereby understanding their emotional states. Despite significant technological advancements in recent years, FER tasks still face several challenges, including expression diversity, individual differences, and the impact of lighting and detail variations on recognition accuracy. To address these challenges, a high-performance FER model is proposed that comprises three key components: High Dynamic Range (HDR) Preprocessing Module, ParallelAttention VisionTransformer structure, and CoExpression Head. In the preprocessing stage, the HDR Preprocessing Module optimizes input images through local contrast and detail enhancement techniques, improving the model's adaptability to lighting and detail variations. During the feature processing stage, the ParallelAttention VisionTransformer structure employs a multi-head self-attention mechanism encoder to effectively capture and process facial expression features at various scales, allowing for a detailed understanding of subtle facial expression differences. Finally, the CoExpression Head utilizes a collaborative expression mechanism to efficiently handle and refine features across different expression states during the feature integration process. Combining these three stages significantly enhances the accuracy of facial expression recognition. Extensive experimental evaluations on public datasets, RAF-DB and AffectNet, demonstrate that the model achieves accuracy rates of 92.11%, 67.25%, and 63.40% on RAF-DB, AffectNet, and AffectNet-8, respectively, exhibiting outstanding performance comparable to other state-of-the-art models.
Some of the metrics are blocked by your
consent settings
Neural Backward Chaining Logic Algorithm Based on Dynamic Knowledge Region Segmentation in Knowledge Graph Completion
(2025-01-01)
Liu, Chunmao
;
Tuntiwongwanich, Somkiat
;
Kantathanawat, Thiyaporn
With the rapid development of the Internet, the information age has arrived in a comprehensive way. The explosive growth of information data has greatly increased people's demand for knowledge management. Knowledge graph, as an effective structured knowledge representation tool, greatly enhances the organization and retrieval capabilities of information. However, in practical applications, knowledge graphs often face problems of knowledge loss and incompleteness, which severely limit their widespread application. To address this issue, this study proposes a neural backward chain inference method based on dynamic knowledge region generation. This method overcomes the bottleneck of performance degradation of traditional static methods on large datasets by introducing a dynamic knowledge region generation mechanism, which significantly improves the completion effect of knowledge graphs. The experiment was conducted on the Unified Medical Language System dataset and the Nations dataset. The results showed that when the size of the Unified Medical Language System dataset reached 2500, the accuracy of the proposed method reached 0.85. It was 6.25%, 20%, and 51.8% higher than the 0.80 of the neural backward chain inference method generated by static knowledge regions, 0.70 of the conditional theorem prover algorithms, and 0.56 of the traditional neural theorems proving algorithm, respectively. In the Nations dataset, the accuracy of the proposed method was 0.80 at the same data scale, which was significantly better than other methods. In addition, the method based on dynamic knowledge region generation reduced the iteration time to 1.4 seconds, which was about 52% and 63% higher than the static method's 2.9 s and the traditional method's 3.8 s, respectively. The research results indicate that the proposed neural backward chain logic algorithm based on dynamic knowledge region generation exhibits good performance in completing knowledge graphs.
Some of the metrics are blocked by your
consent settings
Artificial Intelligence-driven Cognitive Diagnosis anAdaptive Learning: The Impact of Online Course Stickiness and Learning Skills
(2025-01-01)
Liu, Chunmao
;
Tuntiwongwanich, Somkiat
;
Kantathanawat, Thiyaporn
The study analyzes behavioural data that express cognitive connotations, establishes AI-driven cognitive diagnosis and adaptive learning, fills the gap in multimodal data fusion in characterizing cognitive characteristics, constructs a holistic cognitive diagnosis model, and evaluates the impact of AI-driven adaptive learning models on online course stickiness and learning skills. The study innovatively proposes four components of the cognitive diagnosis model: the core theoretical framework of the model composed of cognitive dimensions, the input variables of the model consisting of behavioural data features, the diagnostic model as a method for calculating cognitive states, and the cognitive diagnosis output. The study sorted out the core theoretical framework of the model and proposed behavioural data feature input variables, and completed the cognitive diagnosis output in three dimensions: learning momentum, effectiveness, and strategy through the XGBoost model based on the Gradient Boosting framework.An adaptive online learning model based on behavioural data cognitive diagnosis and knowledge graph is proposed, which includes six parts: input layer, feature extraction layer, cognitive diagnosis module, learning path recommendation module and output layer. The cognitive diagnosis module uses the feature weights calculated by XGBoost as input to predict the mastery of knowledge points through LSTM improved by deep learning recurrent neural network (RNN) and makes learning recommendations based on knowledge graph, cognitive evaluation matrix CEM and collaborative filtering algorithm. Experimental results show that the adaptive learning model of behavioural data cognitive diagnosis has more advantages than traditional online learning, and the adaptive online learning model driven by artificial intelligence behavioural data mining can effectively improve course stickiness, learning skills and platform experience.
Some of the metrics are blocked by your
consent settings
Enhancing Personalized Learning in Online Education: The Impact of Adaptive Learning Systems and Recommendation Technologies
(2024-01-01)
Liu, Chunmao
;
Tuntiwongwanich, Somkiat
;
Kantathanawat, Thiyaporn
The study investigates the impact of integrated adaptive learning systems and recommender technologies on the improvement of online education. A component-level quantitative evaluation was conducted, which involved measuring user interaction, content applicability, knowledge acquisition, and system usability, with support from surveys and interviews. The findings indicate that recommendation systems enhance active user participation, content relevance, and learning outcomes, while maintaining high usability rates that positively influence learners’ perceptions. However, certain limitations were identified, including the system’s less-than-ideal suitability for advanced learners and the absence of contextual information. The study concludes that, when appropriately implemented as suggested by existing literature, adaptive learning systems possess significant potential to transform online education by offering personalised and efficient learning methods. Recommendations for future developments include the integration of third-generation machine learning, ensuring equal opportunities for learners, and further refining the system to address small learner differences.
Some of the metrics are blocked by your
consent settings
Programming Self-Efficacy in Higher Education Research: A Systematic Literature Review
(2023-12-29)
Kantathanawat, Thiyaporn
;
Chinchua, Siwalai
;
Tuntiwongwanich, Somkiat
The goal of the systematic literature review (SLR) was to provide an overview of the concepts and factors associated with programming self-efficacy (PSE) from 2017 to 2021 in Scopus (215) and the Web of Science (310) academic indexes. From the initial 525 articles identified, 405 were left after duplication identification. Using further criteria such as article years must be between 2017 and 2021 in English, and through a peer-review process, 60 remained. These 60 papers were then analyzed using a set of questionnaires, from which 36 articles were excluded. Finally, 24 articles were selected for further analysis and to answer the study’s research questions. Results revealed that student success in information communication technology (ICT) and computer programming courses was from making the learners aware of their programming abilities. Therefore, higher education (HE) institutions should be encouraged to review learners’ abilities in programming and their related perceptions. Finally, institutions should create a relevant learning strategy using tools appropriate for improving education quality.
Some of the metrics are blocked by your
consent settings
Development of an Online Active Learning Model Using the Theory of Multiple Intelligence to Encourage Thai Undergraduate Student Analytical Thinking Skills
(2022-09-30)
Rodrangsee, Bovornwich
;
Tuntiwongwanich, Somkiat
;
Pimdee, Paitoon
;
Moto, Sangutai
This research aim was to create an online active learning (OAL) model using Multiple Intelligence Theory (MIT) to promote Thai undergraduate analytical thinking skills (ATS). Eight experts assisted with their expertise in the model’s development and five for the model’s final assessment. The research tools used consisted of an interview form and a model assessment form. The results showed that the PPICE learning model consisted of nine elements and five steps. The five steps were preparation and problem determination (Step 1), problem analysis (Step 2), study and collect relevant information to practice thinking (Step 3), conclusion and presentations (Step 4), lesson summary and evaluation (Step 5). The expert's assessment of the PPICE Model revealed that overall the model was at its 'best' level (mean = 4.63, SD = .048). Moreover, the experts judged the model's nine components as the 'best' (mean = 4.74, SD = 0.38), with measurement and evaluation second (mean = 4.70, SD = 0.45), and teaching and learning activity processes third (mean = 4.66, SD = 0.48).
Some of the metrics are blocked by your
consent settings
Increasing Programming Self-Efficacy (PSE) Through a Problem-Based Gamification Digital Learning Ecosystem (DLE) Model
(2022-08-21)
Chinchua, Siwalai
;
Kantathanawat, Thiyaporn
;
Tuntiwongwanich, Somkiat
The researchers initially undertook a systematic literature review concerning problem-based learning (PBL), gamification, digital learning ecosystems (DLE), and programming self-efficacy (PSE). Using recent studies and papers from Google Scholar, a preliminary gamified and DLE model was proposed to help Thai students PSE. Further analysis was conducted on gamification mechanics, dynamics, and aesthetics (MDA). After an assessment by nine educational experts using four educational assessment tools from the Joint Committee on Standards for Educational Evaluation (JCSEE) of the proposed seven-step A3S3R (advise, assign, analyze, search, synthesize, summarize, and report) DLE Management Model, the model’s suitability was judged to be ‘very high’ (mean = 4.40, SD = 0.59). Consequently, the development of this learning management model will result in learners recognizing their abilities better in programming and having better programming skills. It can also potentially increase students’ critical and analytical thinking skills and computational thinking and allow them to apply new knowledge or skills to new situations. Finally, researchers can develop new practical learning styles for use in teaching and learning.
Some of the metrics are blocked by your
consent settings
Development of CT Using Need Assessment and Gamification: A Systematic Review
(2021-01-01)
Aroonsiwagool, Athit
;
Tuntiwongwanich, Somkiat
This study originates from the content synthesis of studies on computational thinking, need assessment, gamification, and computational thinking with coding from Thai and international scholarly articles published in accredited databases. Then, the synthesis results were integrated into the development of computational thinking through gamification and programming knowledge to improve the efficacy of computational learning. The process commenced with an analysis of the learners' needs obtained through the questionnaires concerning computational thinking. Data analysis illuminated the learners' levels of computational thinking as well as a fundamental understanding of what the learners need to be taught or what areas of skills each learner. With regards to this, conventional teaching approaches may not serve best to transmit the relevant knowledge which may subsequently induce unfavorable attitudes toward computational thinking. With the data elicited through the need assessment, instructors will have a clear direction as to how the pedagogical process should be designed to directly address the needs in each of the computational thinking components. In general, each component of them is rather complex, so the researcher incorporated gamification theory-based learning defined by its enjoyable game mechanisms and challenging nature which makes the coding lesson fun with block programming enabling learners to proficiently grasp the concept of computational thinking.
Some of the metrics are blocked by your
consent settings
A blended learning model with IoT-based technology: Effectively used when the COVID-19 pandemic?
(2020-01-01)
Siripongdee, Kobchai
;
Pimdee, Paitoon
;
Tuntiwongwanich, Somkiat
IoT-based technology was considered to refer to all heterogeneous objects and devices through any networks, and Blended Learning (BL) is the educational approach to combine face-to-face (F2F) instruction with ICT instruction. In this COVID-19 pandemic, a model of BL with IoT-based maybe the best New Normal solution for all educational stakeholders. While Traditional F2F is forced to change by social distancing to prevent COVID-19. Many IoT-based "things" could be added in class to create and improve a smart learning environment while portable devices could be joined for the learning goals. This study divided BL into 4 characteristics; F2F, Self-paced, Tele-D, and Ubiquitous, which were further categorized into 3 typical cases of learning environments, Digital, Embedded, and Side-by-side cases. Content analysis method was used to analyze and synthesize a model from related literatures, textbooks, research, articles and websites. A framework of this model has 2 roles of user interfaces (teacher and student) which link 6 modules and a set of databases and 2 types of contexts (classroom and personal).
Some of the metrics are blocked by your
consent settings
A Thai junior high school students' 21st century information literacy, media literacy, and ICT literacy skills factor analysis
(2018-01-01)
Moto, Sangutai
;
Ratanaolarn, Thanin
;
Tuntiwongwanich, Somkiat
;
Pimdee, Paitoon
As Thailand moves through the 21st Century, the education system and resultant labor force must be prepared for rapid changes in Thailand's society, culture, politics, economy, and technologies. Previously, the 21st century framework has identified crucial elements for future success as information literacy, media literacy, and information and communication technology (ICT) literacy skills. Given this priority, by use of multistage clustering sampling, 380 Thai junior high school students were selected, from which a five level, 73-item Likert type agreement scale questionnaire was used to collect data from October 2017to December 2017. The analysis of the student's skills in information literacy, media literacy, and ICT literacy was conducted with the use of SPSS Version 24 software mean (χ), standard deviation (S.D.), the Kaiser Meyer Olkin (KMO) test, and Bartlett's test of sphericity for analysis. Furthermore, a second-order confirmatory factor analysis was undertaken in which AMOS Version 24 software was used. Based on the second order CFA, it was found that the Information, Media and Technology Skills (IMTS) model was composed of three components that corresponded to the empirical data, with the most important element being ICT literacy (.998), followed by media literacy (.992), and finally, information literacy (.947).

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results