Modafar Ati

Knowledge capturing in autonomous system design for chronic disease risk assessment

Recent years has witnessed a rapid increase in chronic diseases that populations are suffering from. According to the World Health Organization (WHO), these diseases, such as heart disease, stroke, cancer, chronic respiratory diseases and diabetes, are without doubt the leading cause of mortality in the world, representing 60% of all deaths [1]. Diabetes, however, is one of these chronic diseases that started to increase for the past decades and effecting the life of a large number of people around the world, According to World Health Organization latest record in 2011, there are one in ten adults have diabetes. It was also found that diabetes causes approximately 10% of all deaths globally each year. With respect to the current life style, this percentage is most likely to increase exponentially within the coming few years. However, in order to reduce the effect of such a disease, patients need to be monitored closely and measures should be put into place to control diabetes level. This awareness requires the deployment of a supporting system that assists both Healthcare providers as well as patients. This, in turn, is expecting to increase the load on healthcare providers. The work in this paper presents an approach of building an autonomous system that can be integrated as part of a wider eHealth application. Knowledge capturing plays a vital role for constructing such a system. Hence, this research concentrates on discovering knowledge that held by physicians, and then externalizes tacit knowledge that can be codified in order to form the bases of the autonomous system.

Implementation of Augmented Reality in the Teaching of Young Children

Learning to write can be exhausting for young children. In traditional teaching, children with different learning abilities are taught with the same rubric. This, in turn, impacts children that need extra attention to catch up with their peers, which leads them to suffer right from the early learning stages. Traditional teaching methods also are so rigid which makes them unable to automatically identify those children with less ability and in need of extra help. Hence, with the rapid development of ICT, innovative learning methods are sought to be important to allow children to be taught with different rubrics. The aim of this research is to improve the learning process for pre-school children via introducing Augmented Reality (AR) into the process, which, in turn, simplifies it as well as identifying children’s abilities. The research introduces gamification to the process in order to ease the burden on children. Furthermore, we are trying to involve both the school as well the home to be part of the educational cycle so that parents are a part of the learning/educational process of their young children. Augmented reality combined with pleasing sound make the learning more interactive and enjoyable. The outcome of this research also helps parents to keep track of their children’s learning. The paper also describes the deployment of the application in local schools as a pilot study so teachers can get feedback on students’ learning curves and to fine tune the work further.

Predicting Compressive Strength of Sustainable Self-Consolidating Concrete Using Random Forest

This paper demonstrates the application of Random Forest (RF) algorithm for prediction of compressive strength of sustainable self-consolidating concrete (SCC) in which significant amount of cement was replaced with minerals such as fly ash, ground granulated blast furnace slag (GGBS), and silica fume. SCC improves the quality of the finished concrete product and is considered an environmentally friendly alternative to conventional concrete. RF proved capable of predicting compressive strength with high accuracy. The ability of RF algorithm to predict compressive strength established confidence on the experimental data itself which can be used for further studies on properties of self-consolidating concrete. The high level of accuracy in predicting essential engineering properties of concrete through RF algorithms offers important opportunities to enhance quality in ready mix production industry.

Validation of the Splitting Tensile Strength Formula for Concrete Containing Blast Furnace Slag

The adverse environmental impact of the construction industry may be mitigated through the partial replacement of cement with supplementary cementitious materials (SCM). SCMs such as ground granulated blast furnace slag (GGBS), impart many favourable fresh and long-term concrete properties. A study by Mohamed [1] assessed the splitting tensile strength of sustainable self- consolidating concrete in which up to 80% of the cement was partially replaced with ground granulated blast furnace slag (GGBS), and developed a prediction formula for the splitting tensile strength. In this paper, the tensile strength prediction formula developed by Mohamed et al. [1] is benchmarked against formulas proposed in different building codes and validated with additional test results obtained from the literature. The proposed prediction formula showed excellent correlation to experimental data obtained from the literature.