https://www.um.edu.mt/library/oar/handle/123456789/76579 2026-04-05T14:51:23Z https://www.um.edu.mt/library/oar/handle/123456789/77097 Title: Formal model extraction from informal descriptions Abstract: The translation of natural language specifications to model-based specification can be defined as the translation from unstructured to structured system specification. There is always the possibility of introducing translation errors in this step such as human errors. This project aims to explore and study this translation process in light of proposing an automated mapping paradigm to produce structured models from unstructured natural textual descriptions of system behaviour through the analysis of natural language parts and their mapping to specific formalised model notation. Description: B.Sc. IT (Hons)(Melit.) 2020-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/76929 Title: Enhancing an existing patient dashboard with the use of Internet of Things Abstract: Internet of Things has now become a common trend in the healthcare sector as, with the help of different devices, multiple problems and tasks can be either solved or automated [1]. The aim of this dissertation was to enhance a current web application used at Mater Dei Hospital called the patient dashboard by improving the overall user experience for the medical practitioners while also introducing case studies that make use of Internet of Things. The patient dashboard project was piloted in August 2018 and is currently being used by over 1000 medical practitioners. It is used to connect multiple modules from all departments to store all patient data on a single screen such as medication and blood tests. Many case studies were viewed and analysed to identify where IoT is being used in healthcare and how it can be further implemented within the patient dashboard [2]. Usability studies were also conducted at Mater Dei Hospital on the present patient dashboard to get a better understanding of how and where IoT is being used at the hospital. Results from this study have shown that overall; the application offers a wide-variety of functionality, however, the medical practitioners pointed out certain UI drawbacks that impact the amount of steps required to carry out a task. Upon getting further clarification, the case studies with the most scores given by the participants were designed and implemented creating prototypes to be evaluated later on in the study. The features introduced made use of IoT devices which include QR readers, barcode readers as well as NFC reading and writing. To evaluate this study, another usability review was then carried out on the prototypes developed. The participants found the new UI to be less time consuming (to access certain features) but also relatively clear and easy to read. Last but not least, when attempting the features that made use of IoT devices, medical practitioners were greatly satisfied with the performance and how much they facilitated conditions. Description: B.Sc. IT (Hons)(Melit.) 2020-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/76928 Title: Movie recommendations using machine learning algorithms Abstract: This research attempts to evaluate machine learning technology in a movie recommendation scenario. Previous research in the area has mostly used the MovieLens100K dataset and Mean Absolute Error (MAE) accuracy calculation mechanism; hence for comparison purposes, this research will apply these in its case studies. A review of previous literature shows that good accuracies could be obtained using various methods, however details about internal workings or execution speed are not always given. For this reason, standard machine learning technologies identified via a literature review have been individually examined in a consistent way that would then allow a fair comparison of their accuracy and performance. Furthermore, this research also proposes two novel machine learning technologies, specifically designed for Movie Recommendation. The Matrix technology can rate any kind of movie, even those that it has never encountered in its training while achieving decent accuracy and execution speed. The Movie Centric technology, on the other hand, concentrates on movies it has been trained on and generalises its viewers, achieving a better performance than the Matrix one both in terms of speed as well as MAE. Both technologies can work with just the viewer’s gender as opposed to the group of viewer parameters utilised by other standard technologies. This research has concluded that the Random Forest Classifier provides the best MAE/speed compromise between the standard technologies and the Gradient Boosting Classifier provides the best MAE at the expense of speed. The novel Movie Centric algorithm proposed outperforms the Random Forest Classifier both in speed as well as MAE using only viewer gender. However, it does not reach the accuracy levels of the Gradient Boosting Classifier although it executes much faster. Description: B.Sc. IT (Hons)(Melit.) 2020-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/76927 Title: Automatic crime information gathering and data analytics from online news reports Abstract: One of the major challenges faced by law enforcement is that of the prioritisation and rostering of resources, maximising chances of having the right resources at the right place and at the right time. This research proposes a hybrid machine learning technology which uses a set of customised crawlers to gather data on a daily basis from newspaper articles. Articles that deal with criminal offences are identified, analysed and their inherent details extracted using Natural Language Processing (NLP) Technology. Articles coming from different sources are converged using a standardised format that allows the details of the criminal act (such as crime, location, time, criminal, etc.) to be easily accessed. Related data such as population, literacy etc. are also extracted from other sources using dedicated web crawlers and cross referenced with the criminal events themselves. Web crawling is automated using a special bot designed to initiate the crawling processes regularly. A visualisation engine is being proposed to allow users to quickly and effectively browse the criminal event database using a feature rich search engine enabling specific parameters to be easily identified and depicted. Representations include geographical/calendar heat maps, graphs, etc. Previous research in similar areas has utilised various machine learning techniques with different success rates. This research aims to study the effectiveness of K-Means and DBSCAN [87] based technologies when applied to crime prediction. K-Means uses a purely statistical past-data based model to attempt to predict the incidence of crime; while DBSCAN uses clustering techniques which could include other datasets in addition to past criminal event data. Various datasets has been used to evaluate the performance of the proposed technology; with encouraging results. The Precision/Recall/F-Measure technique used in previous studies [85], [96], has been utilised to compute the F-Measure of both techniques. Moreover, geographically different regions (Malta and Boston) where used to evaluate different crime patterns. While the large number of possible prediction configurations make it very difficult to cover all the possible scenarios, both techniques performed quite well, with the K-Means based one being slightly more accurate when predicting recurring crimes. Predictions of monthly instances of specific crimes were achieved with a combined (NLP + Prediction) F-Measure of 0.78 which compares very favourably with other studies, even those who only covered prediction on a ready-made dataset without any NLP related inaccuracies. Description: B.Sc. IT (Hons)(Melit.) 2020-01-01T00:00:00Z