Azrina Kamaruddin

To ‘dump’ or not to ‘dump’: Changing, supporting or distracting behavior

The way we manage our personal information varies considerably between users. An exploratory study was conducted to investigate the decision making process when storing new items and in particular their dumping behavior, which we define as putting in some unclassified/partially classified storage. It was found that users ‘dump’ when unsure where to store, do not have the time to decide where to store, or not want to lose sight of data - these all have an impact on future retrieval. Understanding this behavior suggests design opportunities to support users, raising awareness of previously encountered but dumped information.

Towards Designing Tangible Interaction for Children with Dyslexia in Learning the Malay Language

In this paper, we provide a study of tangible interaction (TI) based on theories and related works for dyslexic children. The study is an attempt to investigate TI for dyslexic children in learning Malay language in Malaysia primary schools. TI has tremendous contribution in supporting dyslexic children to enhance their way of learning process. However, TI that were developed currently have different capabilities and purposes. For example, current works currently only developed for other languages like English, Mandarin and Dutch. The TI model for English or other languages may not be suitable to be adopted directly for the Malay language due to differences of letter sound, morphology and etc. There were nine related works reviewed in this study. Based on these previous related works and learning theories we designed a conceptual TI model for dyslexic children in learning the Malay language.

Dyslexia Adaptive Learning Model: Student Engagement Prediction Using Machine Learning Approach

Education barriers are synonym with people with dyslexia life experience. People with dyslexia encounter barriers such as in academic related areas, mistreated with negative reaction on their behaviour and limitation to acquire a suitable support to overcome the barriers. Therefore, this work focus on giving the support to help students with dyslexia deal with their difficulty through adaptively sense their behaviour for engagement perspective. For that reason, we apply machine learning approach that utilises Bag of Features (BOF) image classification to predict student engagement towards the learning content. The engagement prediction was relatively using frontal face of the 30 students. We used Speeded-Up Robust Feature (SURF) key point descriptor and clustered using k-Means method for the codebook in this BOF model. Then, we classify the model using 3 types of classifier which are Support Vector Machine (SVM), Naive Bayes and K-Nearest Neighbour (k-NN) to find the best classification result. Through these methods, we managed to get high accuracy with 97–97.8%.

Engagement Prediction in the Adaptive Learning Model for Students with Dyslexia

Student engagement is one of the most important elements in a likelihood of school failure or dropout. Therefore, it is vital to measure the student engagement as quickly as possible and as often as possible to prevent it occurred in a prolonged situation. There a few ways to assess the engagement that includes self-reporting, teachers rating, interviews and observation. However, these methods are not only takings time but also need a lot of hard work, cost and difficult to conduct for a very short time. Therefore, we a proposing an alternative to predict student engagement through frontal face detection. We apply machine learning approach that utilizes Speed-Up Robust Features (SURF) descriptor to detect key interest point of the images and cluster using different codebook sizes. For classification model, we used Support Vector Machine (SVM) with two different kernels and Naïve Bayes. We managed to get more than 88% of the accuracy results. The model is an important part of our proposed adaptive learning model for dyslexic students.

Informing Design of an Adaptive Learning Model for student with Dyslexia: A Preliminary Study

Students with dyslexia are known to have difficulties in phonology, spelling, reading, and writing. Therefore, specific intervention needs to be introduced to the students in order to help overcome their difficulties. The existence of Dyslexia Association of Malaysia (DAM) that provides dyslexic intensive education program becomes a primary place for parents to seek for help in intervention. Based on DAM experience in handling students with dyslexia, we conducted a preliminary study comprises semi-structured interview and observation result to uncover their teaching approaches and materials. The result from this preliminary study will be used to develop the adaptive learning model in order to make an effective learning experience that tailored to individual difficulties

UML Stereotypes for the Development of Process Interaction-Driven Web Applications

Web applications have been developed rapidly as to support a variety of online processes and transactional workflows involved in the web domain. Although there are several numbers of design modeling concepts existing in web application nowadays, new issues such as interrelated process flow, navigational interaction and graphical user interface still become the biggest attention among researchers. This paper presents UML stereotype extensions, which focus on the process interaction-driven design in the proposed design approach called UEWDM. The uniqueness relies on UML stereotypes usability in the design pattern modeling approach. The new design approach is validated through a case study implementation and verified by web designers. Future works of the design model will be explained and briefly summarized at the end of the paper.

Supporting social pretend play with a virtual toy

This paper presents selected results from a study designed to explore childrens social pretend play in a virtual setting. Fourteen children (aged 5--8) played in pairs with a mobile-based game implemented on an Apple iPad. Interviews and video transcriptions were used to assess three types of social pretend play, which included solitary, simple and associative. Our findings revealed the ways children engaged with the virtual toy and demonstrate social pretend play. We discuss the implications of these findings and provide a series of design implications for designers and researchers.

The impact of visual design principles on classical aesthetic design for a web-based educational platform

Studies have been done to investigate the influence of visual aesthetics on web-based educational platform, but little research has been conducted respecting which aspect of aesthetics, namely classical aesthetics, affects learning positively. We discussed the favourable effects of classical aesthetics on learning and proposed that classical aesthetics can be achieved by employing visual design principles to the design. The goal of this paper is thus to set up a classical aesthetic educational website based on visual design principles and studies the relationships among visual design principles and classical aesthetics. A survey was conducted with 213 undergraduates who learn about computer science. The results show that visual design principles have a positive impact on classical aesthetics. This implies that a web-based educational platform with classical aesthetics can be created by applying visual design principles.

Design Metaphor to Improve Usability of User Interface for Paddy Farmers in Malaysia

Metaphor is a representation of object and situation that have meaning and comparable to real thing to convey the message to people. The purpose of using metaphor is to facilitate in making communication more direct and effective for particular user communities. This study reveals design metaphor issues for paddy farmer population in agriculture domain in Malaysia. The work is motivated by the ICT-Based Agriculture Flagship Blueprint of the Malaysia Government, an initiative to equips agriculture stakeholders in Malaysia including farmers with ICT knowledge on multiple platforms e.g. kiosk, personal computer or mobile device. The metaphors design is deemed to have a huge potential to improve user interface usability of agriculture applications for paddy farmers in Malaysia.

USING HEURISTIC EVALUATION TO IMPROVE THE USABILITY OF ELECTRONIC MEDICAL RECORD (EMR) MOBILE INTERFACE OF THE CARDIOTHORACIC SURGERY AND ANESTHESIA SYSTEM (CSAS)

This paper presents initial work on mobile user-interface for electronic medical record for cardio experts. The current problem exits when the existing system is left unused by the users, in our case the cardio surgeons due to bad user interface design which involve a heavy cognitive loads and navigation problems. Medical records contain treatment history and relevant experiences related to the patient care. In order to avoid paper based medical record (PMR) drawbacks, most industrialized nations have implemented electronic medical record (EMR). This research aims to evaluate the existing CSAS system usability using heuristic evaluation and then develop an EMR system that overcomes the interface usability problems by designing an effective user interface that is acceptable to healthcare professionals with tablets as the device. Hence, proposing a new user interface prototype taking into account the findings from the evaluation process.