Browsing by Author "Weng, Jui-Feng"

Now showing 1 - 20 of 20

A rule-based CBR approach for expert finding and problem diagnosis
(2010-03-15)
Tung, Yuan-Hsin
;
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
Lee, Tsung-Ping
;
Liao, Anthony Y. H.
It is important to find the person with right expertise and the appropriate solutions in the specific field to solve a critical situation in a large complex system such as an enterprise level application. In this paper, we apply the experts' knowledge to construct a solution retrieval system for expert finding and problem diagnosis. Firstly, we aim to utilize the experts' problem diagnosis knowledge which can identify the error type of problem to suggest the corresponding expert and retrieve the solution for specific error type. Therefore, how to find an efficient way to use domain knowledge and the corresponding experts has become an important issue. To transform experts' knowledge into the knowledge base of a solution retrieval system, the idea of developing a solution retrieval system based on hybrid approach using RBR (rule-based reasoning) and CBR (case-based reasoning), RCBR (rule-based CBR), is proposed in this research. Furthermore, we incorporate domain expertise into our methodology with role-based access control model to suggest appropriate expert for problem solving, and build a prototype system with expert finding and problem diagnosis for the complex system. The experimental results show that RCBR (rule-based CBR) can improve accuracy of retrieval cases and reduce retrieval time prominently. (C) 2009 Elsevier Ltd. All rights reserved.
Adaptively Learning and Assessing SPSS Operating Skills Using Online SPSS Simulator
(2010-01-01)
Chu, Yian-Shu
;
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
Lin, Huan-Yu
;
Wang, Nien-Chu
Online questionnaire is an emerging method for social science researchers to perform their survey. Although there are many data analysis software tools nowadays, such as SPSS, SAS, and Excel etc., to assist the students in analyzing the data of their surveys. However, the intentions of users for using the software tools cannot be probed and utilized to help the users operating them, so it will cause many errors on the students' analysis results due to the misusage of software and result in that learning how to use the data analysis software tools based upon the students' intentions becomes very time-consuming. Moreover, because the software operating procedures of the students are not recorded, the teachers cannot find out the students' misconceptions. In this paper, we acquire the knowledge of using SPSS software and then apply the Simulator Generator concept proposed in previous research to build an online web-based SPSS software simulator for the students to emulate the operating process of SPSS software. Based upon the acquired frequent patterns of misuse, the teacher can design action routines embedded in the simulator to instantly detect the frequent error action patterns and help the students to rectify their misconceptions. Moreover, the teacher can trace and analyze the students' learning statuses according to the logs generated from online SPSS Simulator. Using Simulator Generator, writing grammar rules is essential, but it is not easy for teachers. The knowledge of using SPSS software are largely identical but with minor differences. Thus, an SPSS Functional Ontology is proposed according to the features of SPSS software and the corresponding grammar rules are constructed in this research. Teachers just need to do some minor adjustments on the differences and the action routines, and then the new simulator will be generated automatically.
An Adaptive Learning Strategy Scheme for Role Playing Learning
(2008)
Weng, Jui-Feng
;
Cho, Li-Hao
;
Tseng, Shian-Shyong
;
Su, Jun-Ming
;
資訊工程學系
Traditionally, the assessment of the advanced knowledge about science such as problem solving or inquiry process is a challenging issue. In this paper, we aim to develop a Role Playing Learning platform called "The Banana Farm" to support the assessment of the nature science learning with collaborative fruit planting and marketing scenario. To support the assessment for inquiry process, our idea is to design the learning platform based on the multi-stage graph model in which the stages of vertices represent the student's actions and decision making during the assessment. Thus, the paths chosen to perform can be seemed as the science inquiry processes of them. Since the actions of the same stage may be executed several times, the model is extended to have self edge. Besides, the environmental status and the effectiveness of the learning objects are also extended by the working status and constraint rules in each stage. Thus, the extended Modified Multi-stage Graph (MMG) is proposed to support the assessment of inquiry process by the portfolio paths chosen in different stages. Next, the portfolio is collected for the collaborative behavior mining to discover the students' frequent collaborative action and interaction patterns during the learning. Combining with the characteristics of students, the assessment of teams with different learning strategy and behavior patterns can be obtained. Finally, the experiment on 40 junior high school students has been done and the findings were presented.
An adaptive web-based learning system for the scientific concepts of water cycle in primary schools
(2007-01-01)
Tarng, Wernhuar
;
Chang, Mei-Yu
;
Lai, Lein-Kui
;
Tseng, Shian-Shyong
;
Weng, Jui-Feng
The objective of this study is to develop an adaptive web-based learning system for the scientific concepts of water cycle in primary schools. It is implemented on a SCORM-based platform to meet international standards and local necessity. The theory behind its operation is based on constructivism. The system uses diagnostic tools to find out the misconceptions of students by two-tiered test items. Adaptive learning modules were developed by rule-based inference engine to provide remedial instructions for students according to their misconceptions. An experiment was conducted to analyze the learning effects of students and the conceptual changes during their learning processes, and the results can be used to improve the design of system and its learning contents.
An Ontology Crystallization Approach to Designing Performance-Based Testing Scenario
(2008)
Weng, Jui-Feng
;
Tseng, Shian-Shyong
;
Su, Jun-Ming
;
資訊工程學系
;
Department of Computer Science
The design of Performance-Based Testing is an interesting and important issue for the assessment of the students' problem solving or inquiry process capabilities. In this paper, we aim to design a wild-like authoring environment based upon the performance Assessment Ontology to support the Collaborative design. However, the ontology inconsistency and incompleteness issues become more serious When constructing the ontology collaboratively. Therefore, the Ontology Crystallization scheme is proposed to support the scenario design with collaborative brainstorming and social agreement evaluation. There are three phases which arc concept boundary extension phase, ontology integration phase. and conflict resolution phase. The collaborative brainstorming is based on the sharing of designed ontology, and the conflict resolution is based on the modified Delphi Method with questionnaire based voting. To demonstrate our scheme, it is applied to the designing of the "Banana Farm" assessment scenario. Finally, the experiment and evaluation shows the effectiveness of the designed result.
Building a personalized music emotion prediction system
(2006)
Yeh, Chan-Chang
;
Tseng, Shian-Shyong
;
Tsai, Pei-Chin
;
Weng, Jui-Feng
;
資訊工程學系
With the development of multimedia technology, research on music is getting more and more popular. Nowadays researchers focus on studying the relationship between music and listeners' emotions but they didn't consider users' differences. Therefore, we propose a Personalized Music Emotion Prediction (P-MEP) System to assist predicting listeners' music emotion concerning with users' differences. To analyze listeners' emotional response to music, the P-MEP rules will be generated in the analysis procedure consisting of 5 phases. During the application procedure, the P-MEP System predicts the new listener's emotional response to music. The result of the experiment shows that the generated P-MEP rules can be used to predict emotional response to music concerning with listeners' differences.
Constructing a role playing interactive learning content model
(2007)
Wu, Dung-Chiuan
;
Lin, Huan-Yu
;
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
Su, Jun-Ming
In the early years, the E-learning contents are always written by static HTMT pages, which can not provide a highly interactive learning activity to fulfil the need of some simulation based learning, e.g., Standard Operation Procedure Training. As we known, the learning objective of simulation based learning can be achieved via Role-Playing Flash interactive learning contents. Since this kind of contents is usually manually created, the construction is time-consuming and costly. Thus, we propose an Object Oriented Interactive Content Model (OOICM) representing the high level game knowledge for authors with the interface of OOICM to assist authors in constructing a Role-Playing learning content easily without writing low level codes. OOICM is composed of three components: Story Control Flow (SCF), Activity, and Scene Object (SO). System layer of OOICM, where we apply Petri Net based rule set to model SCF and use flame knowledge representation to model Activities and SOs, is also defined as the middleware to separate OOICM from low-level implementation. Based on OOICM, we implement a generator with frame engine to help authors to construct the learning content. Finally, we compare the generator with other authoring tools and the experiment result shows the generator has better reusability.
Constructing a Self-Organizing C plus plus Programming Inquiry Behavior Miner on the Forum
(2008)
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
Lin, Huan-Yu
;
Su, Jun-Ming
;
資訊工程學系
The web forum is the popular platform used for C++ program learning in which learners can discuss and solve the encountered problems collaboratively. The process of discussions for specific topics in the forum is most likely the inquiry-based learning. Discovering the students' inquiry behavior models in the forum is helpful for teachers to support the guidance during the inquiry-based learning. In this paper, the clustering analysis is applied to discover the behavior patterns on the forum. Before the clustering, we first apply the divide and conquer mining strategy to classify the documents into purposes and sub-purposes until the number of documents is affordable for clustering analysis. To incrementally maintain the topics of inquiry behavior and efficiently analyze the new inquiry topic, the self-organizing ontology maintenance scheme is proposed The topics discussed with multiple purposes are identified as inquiry behavior of hot topics. Finally, the experiment of inquiry behavior mining from legacy forums has been evaluated and the experimental result shows the usefulness of the obtained behavior information.
Constructing an Immersive Poetry Learning Multimedia Environment using Ontology-based Approach
(2008)
Weng, Jui-Feng
;
Tseng, Shian-Shyong
;
Su, Jun-Ming
;
Wang, Yuh-Jye
;
資訊工程學系
Chinese has a rise in popularity due to the spring up of the Chinese language education. In the poetry of the Tang Dynasty, there is a lot of information in the limited number of Chinese characters. Therefore, how to assist learners in understanding of the background story and emotional feature of poetry is a challenging issue. In this paper, to support the poetry appreciation learning, our idea is to provide the Immersive Poetry Learning with multimedia properties: the Vision such as scenic spot, the Reading with occasional poetry, and the Emotional Reinforcement such as background music. To construct the immersive poetry learning with multimedia environment, the Learning Context ontology, the Poetry Noun Ontology and the Music Emotion ontology are defined to annotate the context information poetry contents and music emotional properties. Thus, the Ontology-based Immersive Poetry Learning system can base on the learner contexts to generate the coherent poetry and music by the ontology mapping.
Design and implementation of an object oriented learning activity system
(2006)
Lin, HuanYu
;
Tseng, Shian-Shyong
;
Su, Jun-Ming
;
Weng, Jui-Feng
;
資訊工程學系
For the pedagogical needs, many researches have applied the IMS Learning Design Specification (LD) to express the higher level learning activities. Although the specification of LD can express various learning activities, its technical-driven nature results in the hardness of understanding for teachers. For solving this problem, we propose an Object Oriented Learning Activity model (OOLA) which is a directed graph structure including the following components to model the learning activities: Learning Activity Node (N-LA), Application Node (N-AP), Examination Activity Node (N-EA) and Directed edges connecting the nodes. Based on the OOLA model, we also design and implement an OOLA authoring system, and an OOLA learning system. The OOLA learning system provides the display of learning activities and contents following the learning flow designed by teachers. The OOLA2NORM algorithm is also proposed to transform the course modeled by OOLA to the New Object Oriented Rule Model (NORM). The learning activity of OOLA is then stored in Learning Activity Rule Base (LARB) where each learning activity can be played on the inference engine. For evaluating the OOLA model, the pedagogical theory of Scaffolding Instruction has been implemented. The experimental results show that the OOLA learning system can improve the students' learning.
Design and Implementation of an Object Oriented Learning Activity System
(2009)
Lin, Huan-Yu
;
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
Su, Jun-Ming
;
資訊工程學系
With the development of e-learning technology, many specifications of instructional design have been proposed to make learning activity sharable and reusable. With the specifications and sufficient learning resources, the researches further focus on how to provide learners more appropriate learning activities to improve their learning performance. In this paper, we aim to propose a model which can explicitly represent the knowledge of the mechanism to adapt both the learning activity navigation and content presentation according to learners' knowledge of concepts. In our proposed model, each learning unit object contains the learning items and the related concepts, which can be used to perform adaptive content selection, and the sequencing control of these learning unit objects can be explicitly represented as a directed graph to improve the understandability. Based on the learning sequencing graph, an Object Oriented Learning Activity system is implemented and used to design and perform the learning activity of Scaffolding Instruction, named "The evaporation, condensation and boil of water". The Evaluation results show that teachers can effectively design an adaptive learning activity based on concept and misconception hierarchy and the designed learning activity can really improve learners' learning efficacy by the OOLA system.
Designing a U-Museum Service Framework to Bridge Digital Learning Divide
(2008)
Weng, Jui-Feng
;
Tseng, Shian-Shyong
;
Liao, Anthony Y. H.
;
Su, Jun-Ming
;
資訊工程學系
Due to lack of opportunities in utilizing digital learning auxiliary tools, it causes the existence of so called "Digital Learning Divide" between the students of rural or remote areas and those of urban areas. In this research, it is found that the public learning facilities in the community, for example, the museums, can provide related digital learning resources in spite of the shortage of digital learning facilities at the schools and families in rural or remote areas. If the students in the rural or remote areas are assisted to utilize the learning resources, it can bridge the digital learning divide effectively. However, it is different from the education in the school; the education in the museum is informal education which is emphasized on the learner-centered self-learning. In recent years, due to the advance and availability of RFID technology, and the functions of RFID in recognizing the learners' identities, locations, and movement, it can provide U-Learning services to learners with their personal information. Therefore, in this research, IMS Learner Information Package (LIP) standard is referred to construct a Learner Information Management Framework (LIMF), in which the Learner Model is composed of learner's Profile, Preference, Learning Activity, and Learning Portfolio as the standard fields of learner's information. The Processing Model in LIMF contains the functions of learner identification service, learner activity aware service, and learning resource provision service, and furthermore the web service technology is employed to provide better U-Learning support in accessibility, standardization, and extensibility.
Finding trustworthy experts to help problem solving on the programming learning forum
(2010)
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
資訊工程學系
;
Department of Computer Science
The most important thing for learners in Programming Language subject is problem solving. During the practical programming project, various problems may occur and learners usually need consultation from the senior programmers (i.e. the experts) to assist them in solving the problems. Thus, the inquiry-based learning with learning forum is applied to assist the programming problem solving. However, even if the learning community of the forum is provided, the finding of trustworthy and available experts for improving the quality of social interactions is still difficult for students. Therefore, the idea of applying the social network service of Web 2.0 with the trustworthy experts finding service is proposed to actively consult the experts based on their topic of interest, trustworthiness, and availability. The experts' topic interest and trustworthy degree are obtained from the experts' posting documents on the forum. To maintain the dynamic discussion topics and avoid the synonym problem on the forum, the Programming Capability Ontology is constructed as the consensus taxonomy by the distributed clustering algorithm. The self-organized ontology maintenance scheme is also proposed to maintain and update the new topic keywords in the ontology. The availability of experts can be approximately calculated from their online presence log. Moreover, the updating of the experts' presence value is modeled by the fading probability function of the Ant Colony Algorithm. Finally, the quality of the expert finding service and learners' satisfaction with the expert finding service has been evaluated. The experimental result shows that the feasibility and the effectiveness of the proposed approach are satisfactory.
Interview-Based Photo Tagging for Expressing Course Concepts in Ubiquitous Chinese Poetry Learning
(2008)
Shih, Wen-Chung
;
Tseng, Shian-Shyong
;
Yang, Che-Ching
;
Weng, Jui-Feng
;
Liang, Tyne
Traditional Chinese poetry instruction mainly focuses on vocabulary explanation and recitation, through which it is not easy for students to catch the embedded meaning of the poems. Ubiquitous learning. emerging as a promising learning, paradigm. can provide an adaptive environment according to the learner's context. When the learner is situated in till environment similar to what the poem describes. it will be easier for the learner to understand what the poet meant, thus enhancing the learning performance. To support the poetry appreciation in U-Learning, environments. our idea is to provide an interview-based tool which can assist students to clearly express their intended concepts for a Chinese poem. We reduce the Course Concept Expression problem to the interview-based tagging problem. The interview-based methodology consists of several iterations to find the user's intended concept for a poem. A prototype has been implemented, which will be used to evaluate the effectiveness of the proposed approach in the near future.
Multimedia-Poetry Composition and Sharing on Ubiquitous Environment
(2009)
Tseng, Shian-Shyong
;
Yang, Che-Ching
;
Weng, Jui-Feng
;
Liang, Tyne
;
資訊工程學系
Deeply meanings of Chinese poems are hard to understand for novices. Motivating from the proverb "A picture is worth a thousand words", poetry composition together with relevant multimedia is proposed to assist people in understanding Chinese poems. Learning in this way, the format of poet?), and context of learning environment can be used to provide composition suggestions. Therefore, how to assist people in multimedia-poems composition and sharing on ubiquitous environment becomes a challenging issue. To retrieve context information, a context-based dialogue approach is proposed. Through progressively retrieving context information, composition suggestions can be offered based on rhyme scheme, tonal pattern and context information. Multimedia-poetry can be shared with each other. To evaluate the applicability of the proposed approach, experiments are conducted to understand user's satisfaction degree. The experiment results show that users are satisfied with the proposed system.
Program Peer Assessment Using Tagging Approach
(2008)
Liu, Yi-Li
;
Tseng, Shian-Shyong
;
Lin, Huan-Yu
;
Weng, Jui-Feng
;
Chu, Yian-Shu
Most of die programming novices feel hard to learn programming skills, such as coding, tracing, debugging and testing. To help them learn programming well, computer program assessments which can find out the novices' programming misconception have been proposed. Although traditional computer program assessment can scow die student's program by executing die program with test cases, it is ineffective because die novices' programming misconception in the coding mistakes and tracing mistakes can not be singled out In die peer assessment activity, die learners can discuss their works with each other, so every learner can get die comments; about his/her work together with die score. This paper proposes a new computer program peer assessment to help die novices easily find out their programming misconception in the coding mistakes and tracing mistakes. An experiment has been done to evaluate the effectiveness of die new assessment. We may conclude that die process is useful to single out die leamer's coding and tracing problems, and that the tracing guidance is useful to direct the novice to trace peer's program.
Scratch-Based Interactive Storytelling Assessment
(2010)
Kuo, Hsiu-lien
;
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
理學院
;
College of Science
The disaster precautions education is an important extended learning resource for fifth grade students in Nature Science course. There are e-learning websites and educational games trying to let students engage subject. However, traditional learning activity usually lacks the deep knowledge of cause and effects for students to think and thus does not interest students. In this paper, the Scratch-based Interactive Storytelling Assessment is proposed. The assessment framework for the cause and effect of the students' storytelling creations is designed and implemented on the Scratch digital multimedia creation platform. The experiment evaluation is conducted to 10 fifth grade students. The experiment results show that students are very interested in the storytelling creations. The assessment results also show the contribution of improvement for the training of students' knowledge and reasoning capabilities of the domain.
Teaching Boolean Logic through Game Rule Tuning
(2010-10-01)
Weng, Jui-Feng
;
Tseng, Shian-Shyong
;
Lee, Tsung-Ju
;
資訊工程學系
;
Department of Computer Science
The Boolean logic is a tool to model the algebra of truth values. It is an essential subject in Computer Programming and Digital Electronics. While teaching the Boolean logic, teacher usually gives examples to elaborate the Boolean logic formulation. However, the physical meaning of the Boolean logic is difficult for students to imagine without the realization to real-world case. The classical Pac-Man game which has clear Boolean logic game rules and simple game scenario is chosen as the teaching aid. Accordingly, two learning activities, the Boolean logic realization activity and game scenario formulation activity, are proposed. Our idea is that through game rule tuning in the learning activities, the students can comprehend how the changing of game rule (Boolean logic) affects the game scenario. To manipulate the game scenario for teaching specific learning objectives of Boolean logic, the Game Rule of the original Pac-Man game is defined and seven versions of modified game scenarios provided as illustrations are appropriately organized for students to practice one Boolean logic concept each time. The experimental results showed the proposed activity can have higher learning achievements compared to the traditional lecturing.
Teaching Boolean Logic through Game Rule Tuning
(2010-10-01)
Weng, Jui-Feng
;
Tseng, Shian-Shyong
;
Lee, Tsung-Ju
;
資訊工程學系
;
Department of Computer Science
The Boolean logic is a tool to model the algebra of truth values. It is an essential subject in Computer Programming and Digital Electronics. While teaching the Boolean logic, teacher usually gives examples to elaborate the Boolean logic formulation. However, the physical meaning of the Boolean logic is difficult for students to imagine without the realization to real-world case. The classical Pac-Man game which has clear Boolean logic game rules and simple game scenario is chosen as the teaching aid. Accordingly, two learning activities, the Boolean logic realization activity and game scenario formulation activity, are proposed. Our idea is that through game rule tuning in the learning activities, the students can comprehend how the changing of game rule (Boolean logic) affects the game scenario. To manipulate the game scenario for teaching specific learning objectives of Boolean logic, the Game Rule of the original Pac-Man game is defined and seven versions of modified game scenarios provided as illustrations are appropriately organized for students to practice one Boolean logic concept each time. The experimental results showed the proposed activity can have higher learning achievements compared to the traditional lecturing.
Wiki-based design of Scientific Inquiry assessment by game-based Scratch programming
(2009)
Tseng, Shian-Shyong
;
Weng, Jui-Feng
;
資訊工程學系
;
Department of Computer Science
In the training of scientific literacy, the game-based platform which can dynamically reflect and interact with students' behaviors has been applied to support the scientific inquiry assessment in recent years. Since the design of game scenarios for scientific inquiry assessment usually needs multidisciplinary domain knowledge, the wiki-based platform is applied to support collaborative designing. However, there are scenario linkage issues for designs in consecutive game layers and multidisciplinary convergence issue for multidisciplinary game logic designs. To solve the first issue, the wiki-based prototyping scheme is proposed to manage the linkage using framework design. For the second issue, the multidisciplinary Delphi method is proposed to select the desired game logic by questionnaire approach. To support the multidisciplinary consensus, the multidisciplinary indicators are proposed to reveal the experts' certainty degree in different point of views. The scheme has been applied to designing several scientific inquiry subjects in the Physics domain. The results show that the proposed scheme is efficient and effective.