Choo-Yee Ting

Adaptive digital game-based learning framework

A common teaching and learning methodology involves one that delivers knowledge to learners within a classroom environment. With the enhancement of information technology, Web-based learning has been promoted as an alternative teaching and learning methodology. Digital games, an interactive piece of technology within the multimedia learning environment, could foster the learning process effectively and interestingly especially among young learners. Researchers and game designers have noted this promising technology and proposed some frameworks and models to foster multimedia learning environment. However, most of the models do not address the learning behavior in game design, which is important to facilitate learning process in game-based learning. In view of this, this paper focuses on proposing and discussing components that leverage the pedagogical aspects in designing game-based learning environment.

A cascaded classifier approach for improving detection rates on rare attack categories in network intrusion detection

Network intrusion detection research work that employed KDDCup 99 dataset often encounter challenges in creating classifiers that could handle unequal distributed attack categories. The accuracy of a classification model could be jeopardized if the distribution of attack categories in a training dataset is heavily imbalanced where the rare categories are less than 2% of the total population. In such cases, the model could not efficiently learn the characteristics of rare categories and this will result in poor detection rates. In this research, we introduce an efficient and effective approach in dealing with the unequal distribution of attack categories. Our approach relies on the training of cascaded classifiers using a dichotomized training dataset in each cascading stage. The training dataset is dichotomized based on the rare and non-rare attack categories. The empirical findings support our arguments that training cascaded classifiers using the dichotomized dataset provides higher detection rates on the rare categories as well as comparably higher detection rates for the non-rare attack categories as compared to the findings reported in other research works. The higher detection rates are due to the mitigation of the influence from the dominant categories if the rare attack categories are separated from the dataset.

Learning Difficulties in Programming Courses: Undergraduates' Perspective and Perception

Researchers have been searching for alternatives in teaching programming subjects. A reason to this is due to the fact that the compulsory subject in the field of Information Technology has been a challenge and they are tough subjects to learn. On top of that, lacking the understanding in concepts has reduced undergraduates’ interests to pursue further exploration and self-experimentation. In this research work, a study was conducted to investigate the factors that lead to undergraduates’ learning difficulty in programming courses and also their perception on which teaching methodology could be implemented to create richer and interesting learning process. The study involved 182 undergraduates from Multimedia University, Malaysia, who have taken the fundamental programming subject named Computer Programming I. The findings affirmed that undergraduates prefer to learn programming by referring to examples and using drill-practice method whereas learning via lecturing would only decrease their interest level. The challenge has provided an evidence to call for a better solution, game-based learning as an alternative to teach and learn computer programming subjects. Therefore, the authors proposed a game-based learning framework which consists of components that leverage the pedagogical aspects in designing game-based learning environment for programming subjects.

Handwritten music notation recognition using HMM — a non-gestural approach

We investigate the recognition of handwritten musical notation using Hidden Markov Models (HMMs). In a non-gestural approach, handwritten musical notation is entered naturally via a pen tablet as we would do using pen and paper. A sequence of observed ink patterns representing musical symbols is captured and used to construct different HMM models. The proposed approach exploits both global and local information derived from ink patterns which we have demonstrated the exploitation of this information via different features employed in different HMMs. The specificity and sensitivity measures of these different classification models are compared using unseen test sets. The experiment shows that using non-gestural method is a very good approach to obtain handwritten music notation input, as it is most natural and does not require user training. It is also shown that HMM is very suitable to be used as the classifier in this domain, showing very high recognition rates. Additionally, the experimental results also concluded that models from HMMs with more hidden states also outperform the HMM with a lesser number of hidden states since a larger model has more capacity. The results also suggest that HMMs offer flexibility in encoding useful knowledge in the models.

A decision-theoretic approach to scientific inquiry exploratory learning environment

Although existing computer-based scientific inquiry learning environments have proven to benefit learners, effectively inferring and intervening within these learning environments remain an open issue. To tackle this challenge, this article will firstly address the issue on learning model by proposing Scientific Inquiry Exploratory Learning Model. Secondly, aiming at effective modeling and intervening under uncertainty in modeling learners exploratory behaviours, decision-theoretic approach is integrated into INQPRO. This approach allows INQPRO to compute a probabilistic assessment on learners scientific inquiry skills (Hypothesis Generation and Variables Identification), domain knowledge, and subsequently provides tailored hints. This article ends with an investigation on the accuracy of proposed learner model by performing a model walk-through with human expert and field trial evaluation with a total number of 30 human students.

A Feature Selection Approach for Network Intrusion Detection

Processing huge amount of collected network data to identify network intrusions needs high computational cost. Reducing features in the collected data may therefore solve the problem. We proposed an approach for obtaining optimal number of features to build an efficient model for intrusion detection system (IDS). Two feature selection algorithms were involved to generate two feature sets. These two features sets were then utilized to produce a combined and a shared feature set, respectively. The shared feature set consisted of features agreed by the two feature selection algorithms and therefore considered important features for identifying intrusions. Human intervention was then conducted to find an optimal number of features in between the combined (maximum) and shared feature sets (minimum). Empirical results showed that the proposed feature set gave equivalent results compared to the feature sets generated by the selected feature selection methods, and combined feature sets.

Properties of Bayesian student model for INQPRO

Employing a probabilistic student model in a scientific inquiry learning environment often presents two challenges. First, what constitute the appropriate variables for modeling scientific inquiry skills in such a learning environment, considering the fact that it practices exploratory learning approach? Following exploratory learning approach, students are granted the freedom to navigate from one GUI to another. Second, do causal dependencies exist between the identified variables, and if they do, how should they be defined? To tackle the challenges, this research work attempted the Bayesian Networks framework. Leveraging on the framework, two student models were constructed to predict the acquisition of scientific inquiry skills for INQPRO, a scientific inquiry learning environment developed in this research work. The student models can be differentiated by the variables they modeled and the causal dependencies they encoded. An on-field evaluation involving 101 students was performed to assess the most appropriate structure of the INQPRO’s student model. To ensure fairness in model comparison, the same Dynamic Bayesian Network (DBN) construction approach was employed. Lastly, this paper highlights the properties of the student model that provide optimal results for modeling scientific inquiry skill acquisition in INQPRO.

Factors influencing the performance of Dynamic Decision Network for INQPRO

There has been an increasing interest in employing decision-theoretic framework for learner modeling and provision of pedagogical support in Intelligent Tutoring Systems (ITSs). Much of the existing learner modeling research work focuses on identifying appropriate learner properties. Little attention, however, has been given to leverage Dynamic Decision Network (DDN) as a dynamic learner model to reason and intervene across time. Employing a DDN-based learner model in a scientific inquiry learning environment, however, remains at infant stage because there are factors contributed to the performance the learner model. Three factors have been identified to influence the matching accuracy of INQPROs learner model. These factors are thestructureof DDN model, thevariable instantiationapproach, and theweightsassignmentmethodfortwoconsecutiveDecisionNetworks (DNs). In this research work, a two-phase empirical study involving 107 learners and six domain experts was conducted to determine the optimal conditions for the INQPROs dynamic learner model. The empirical results suggested each time-slice of the INQPROs DDN should consist of a DN, and that DN should correspond to the Graphical User Interface (GUI) accessed. In light of evidence, observable variables should be instantiated to their observedstates; leaving the remaining observable nodes uninstantiated. The empirical results also indicated that varying weights between two consecutive DNs could optimize the matching accuracy of INQPROs dynamic learner model.

Soft skills recommendation systems for IT jobs: A Bayesian network approach

Today, soft skills are crucial factors to the success of a project. For a certain set of jobs, soft skills are often considered more crucial than the hard skills or technical skills, in order to perform the job effectively. However, it is not a trivial task to identify the appropriate soft skills for each job. In this light, this study proposed a solution to assist employers when preparing advertisement via identification of suitable soft skills together with its relevancy to that particular job title. Bayesian network is employed to solve this problem because it is suitable for reasoning and decision making under uncertainty. The proposed Bayesian Network is trained using a dataset collected via extracting information from advertisements and also through interview sessions with a few identified experts.

Optimal dynamic decision network model for scientific inquiry learning environment

While recent studies employ heuristic to support learners in scientific inquiry learning environments, this study examined the theoretical and practical aspects of decision-theoretic approach to simultaneous reason about learners’ scientific inquiry skills and provision of adaptive pedagogical interventions across time. In this study, the dynamic learner model, represented by three different Dynamic Decision Network (DDN) models, were employed and evaluated through a three-phase empirical study. This paper discusses how insights gained and lessons learned from the evaluations of a preceding model had led to the improvements of subsequent model; before finalizing the optimal design of DDN model. The empirical studies involved six domain experts, 101 first-year university learners, and dataset from our previous research. Each learner participated in a series of activities including a pretest, a session with INQPRO learning environment, a posttest, and an interview session. For each DDN model, the predictive accuracies were computed by comparing the classifications given by the model with (a) the results obtained from the pretest, posttest, and learner self-rating scores, and (b) classifications elicited by domain experts based on the learner interaction logs and the graphs exhibited by each model.