/library/oar/handle/123456789/91571 2025-11-06T04:07:38Z 2025-11-06T04:07:38Z /library/oar/handle/123456789/92916 2022-04-05T04:53:59Z 2021-01-01T00:00:00Z

Title: Developing an educational game teaching Maltese to children with intellectual disabilities Abstract: Educational advancements have been acknowledged since the initiation of inclusive education in Malta, yet several concerns and hardships for students with disabilities remain. Reasoning and interpretation of information is challenging for intellectually disabled children thus they require direct teaching and assistance. Language learning is a struggle since they have deficiencies in communication and language abilities related to vocabulary, sentence building, and understanding complex instructions, leading to lack of proficiency and self-esteem in conversing and public speaking. With the growth in technologies for impaired individuals, it is imperative that these are adapted for children with disabilities, and any applications utilised by such users must be designed accordingly, taking into consideration specific disabilities and requirements. Since children with intellectual disabilities use mobile technology daily, this research project involves supplying a digital educational game teaching Maltese to intellectually disabled children, which may be used within a classroom environment or at home. It comprises of evaluating how it facilitates the education of the language among children with various intellectual disabilities, within a limited time span. Research on game-based learning, traditional educational theories and learning strategies has been carried out to ensure that these are applied effectively. Techniques for how these are implemented, and optimal design considerations, are also explored by holding workshops with Learning Support Educators experienced with educating children with intellectual disabilities. A core challenge in developing such an application is the ability to engage and motivate players to utilise and enjoy the application whilst learning the language. The solution includes audio and visual aspects to immerse its users. The text-to-speech functionality and sounds played depending on users’ answers provide an enhanced learning experience. Moreover, drag-and-drop components and rewards motivate students, stimulating them to learn further. Another challenge is the various learning abilities and paces that children with intellectual disabilities have, which affects the overall perception towards the game. If pupils are tasked with challenging activities beyond their capabilities, they often become disengaged and lose interest. The solution proposed enables educators to add levels and remove pre-existing ones to ascertain that the game provides activities within the ability of the user. An Iterative Software Development Life Cycle approach was implemented, in which wireframes were designed for requirements elicitation, and several prototypes were developed and amended following educators’ feedback. The LSEs made use of the system themselves and analysed their pupils playing the games, observing their reactions and noting any progress made. A usability study and educator evaluation then followed, which concluded that the application was indeed successful in achieving its objective of facilitating teaching and engaging pupils to learn Maltese, whilst ensuring that the system is usable and effective. Description: B.Sc. IT (Hons)(Melit.)

2021-01-01T00:00:00Z /library/oar/handle/123456789/92407 2022-03-28T05:34:48Z 2021-01-01T00:00:00Z

Title: Predicting blood glucose levels using machine learning techniques with metaheuristic optimisers Abstract: Introduction: Persons with Type-1 diabetes need to continuously monitor their blood glucose level to remain within a healthy range. Using machine learning techniques researchers can predict blood glucose values with the benefit of providing the patient with future blood glucose values with the aim of primitively taking action. The focus of this study was to investigate the use of metaheuristic optimisers to strategically tune the hyperparameter configuration of these machine learners in the context of blood glucose prediction using the OhioT1DM dataset with the aim of improving the predictive performance of the machine learners. Research questions: i) What is the degree of improvement when using a metaheuristic approach over a completely random search given the same search space? ii) How can the computation be carried out in a shorter time, what are possible ways of distributing the workload among several machines? Methodology: A few machine learners namely the MLP, RNN and XGBoost were implemented for the prediction of blood glucose level. Moreover, two metaheuristic optimisers, the genetic algorithm and particle swarm optimisation, and random search were used to perform hyperparameter optimisation. The experimentation was run three times to obtain an average of the performance. Due to the increased computation load in running multiple runs a Spark cluster running on EC2 instances was considered to reduce the computation time. Results & evaluation: The results obtained from the experimentation give an indication that for the context of the ohioT1DM dataset and configurations set, the metaheuristic optimisers consistently provide a slightly better predictive performance when given enough iterations. Conclusion: This study demonstrated that the use of metaheuristic optimisers in the context of blood glucose prediction when using the OhioT1DM dataset can provide improved results over random search. It is noted that using such techniques significantly increased computational load. Description: B.Sc. IT (Hons)(Melit.)

2021-01-01T00:00:00Z /library/oar/handle/123456789/92406 2022-03-28T05:34:11Z 2021-01-01T00:00:00Z

Title: Tools to construct the comparative analysis of existing medical portals Abstract: The aim of portals, which are made up of information sources, is to offer a structured interface to which the user has access. Nevertheless, concerns remain about what factors can contribute to portal long-term use. Portal infrastructures are centred around Web technologies with the familiar interface being the Web browser. As a case study, this project focuses on the development of medical portals that allow the medical community with access to medical records through the Web browser. Medical portals are felt to be a valid representative class of Web portals as their information is by its nature large, non-trivial, and distributed. Furthermore, medical patient portals draw their effectiveness from the extent of patient involvement they engender. As grounding, this project explores the background defining what a web portal is through its functional and non-functional properties and defines various web portal classifications. Following a survey of previous researchers found in developing these types of information products, coupled with a study of technologies required to construct portals, using medical portals as a representative case, the issue of web portal usability and longevity was addressed. By analysing previous studies, it was concluded that the most important characteristics when developing an effective portal were the targeted users’ level of maturity, portal usage and portal overall security. By understanding the motivation for the use of web portals, the project explores the application of techniques such as activity theory which seeks to comprehend human interaction through analysis of their activities to increase the effectiveness of web portals. In the case of medical portals, studies have shown that activity theory is an effective tool for depicting the non-trivial nature of medical environments. For this reason, a system will be developed using an activity theory approach and implemented through the use of appropriate frameworks. For portals to be accessible, they must be constructed in a manner that makes them simple to use while always fulfilling both requirements and usage constraints. Description: B.Sc. IT (Hons)(Melit.)

2021-01-01T00:00:00Z /library/oar/handle/123456789/92375 2022-03-28T05:25:17Z 2021-01-01T00:00:00Z

Title: A data analytic approach to property price prediction, influenced by geographic elements Abstract: Property sales in Malta throughout the COVID-19 pandemic, topped €3 billion in 2020, surpassing 2019 figures. Despite this influx in property sales, interviews with local real estate executives revealed that the majority of local real estate agencies value property listings manually, without the help of any ML technologies. It also emerged that the value of a property is heavily influenced by its location, which location is characterised by amenities. The exploration for the best predictive model is a popular approach in research, though few explore the influence of external amenities on this prediction. This study intended to explore the influence of amenities on property valuation by exploring whether predictive accuracy improves when considering proximal amenities. Real estate data for the period 2015 to 2020 was sourced from a local real estate agency. Records containing blank attributes, location outliers and property types in limited supply such as farmhouses were removed. Prices were adjusted to mitigate the effect of price increases over the period. An online map service was utilised to obtain latitude and longitude values for all property listings (geocoding), as well as to extract amenities around the Maltese islands and their respective coordinates. Four types of amenities were considered; bus stops, shops, natural features and other amenities such as restaurants, bars and cafes. A tier system, shown in Figure 1 was used, where for each listing, the quantities of amenities which fall within each of the proximity thresholds, 100m, 200m and 400m, were stored. Two types of predictive models were developed; multi-layer perceptron (MLP) neural networks and multiple linear regression (MLR) models where a number of model configurations considering property data with no amenities, individual groups of amenities or all amenities were configured. The models’ performance was determined by considering the mean absolute percentage error (MAPE) and root mean squared error (RMSE) produced, considering the magnitude and standard deviation of errors respectively. It was observed that the less attributes the MLR models were given, these models tended to fare better. The base model which considered solely property-specific data such as property type, locality, number of bedrooms, bathrooms, coordinates and square area performed the best with a 22.81% MAPE, seeing all other models produce higher MAPE readings. On the other hand, the MLP base model registered a 19.21% MAPE, whilst the best performing model developed, considering a number of amenities at different proximity measures, scored an 11.69%. Therefore, since the MAPE reduced by 7.52% and RMSE reduced by around 50% when considering proximal amenities, this may suggest that such consideration contributes towards a more accurate prediction. Hence, this was indicative that the optimised MLP model was the better overall performer, registering around 11% less error when comparing the best performing MLP and MLR models. Description: B.Sc. IT (Hons)(Melit.)

2021-01-01T00:00:00Z