https://www.um.edu.mt/library/oar/handle/123456789/121801 2026-04-04T22:04:47Z https://www.um.edu.mt/library/oar/handle/123456789/142036 Title: Multi-vehicle ride-pooling system using reinforcement learning Abstract: Ride-pooling services have surged in popularity in recent years due to them being more efficient, convenient, and cost-effective than alternative traditional methods such as taxis. Leveraging mobile technologies, ride pooling services use the location of drivers and customers to assign a shared vehicle to passengers travelling in the same direction, reducing the number of vehicles on the road and, therefore, helping reduce traffic congestion. Such services require algorithms that dynamically match passengers with nearby drivers and optimise routes. Ride-pooling can be considered a variant of the Vehicle Routing Problem (VRP), which is a combinatorial NP-hard problem as it involves finding an efficient set of routes for a fleet of vehicles to serve customers while satisfying constraints such as customers’ time windows and vehicle capacity. Literature shows how the use of various metaheuristic algorithms to solve the VRP, such as tabu search (TS), can provide good solutions in terms of quality but suffer from scalability. With the recent advances in artificial intelligence, Reinforcement Learning (RL) is also being applied to capture the dynamic and stochastic nature of the VRP. In this research, we propose to use RL to solve the Multi-Vehicle Routing for Ride-Pooling Problem (MVRRPP) and generate solutions faster than the traditional metaheuristic methods. This algorithm aims to optimise passenger allocation to vehicles and vehicle routing while minimising the overall waiting time, travel time and total driving distance. We first implemented a baseline algorithm that uses TS with an initial solution consisting of equally distributed customers along the routes to solve the MVRRPP and establish its performance. We then model the MVRRPP as an RL problem and solve it using the REINFORCE algorithm with a dynamic attention model consisting of a dynamic encoder-decoder architecture. The performance of this model was compared with the results achieved using TS. Finally, we evaluate the effect of using an RL solution as input for the TS algorithm. The results of the three models showed that TS found higher-quality solutions than RL and TS with RL; however, its computational complexity resulted in longer computation times when solving large problem instances. Using RL involved a trade-off between solution quality and computation time, where it was quicker to find a solution even for problems on a large scale. On the other hand, performance using TS with RL showed minimal improvement except for reducing the distance travelled by vehicles, which suggests that the RL solution, used as the initial solution for TS, was in a region of the search space that had an inferior local optimum then the initial solution used in the TS without RL. The choice between TS and RL for solving the MVRRPP depends on the application’s requirements and the problem’s complexity. Description: M.Sc.(Melit.) 2024-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/140266 Title: Real-time multi-camera tracking and od-matrix estimation of vehicles Abstract: With computer vision, it is possible to capture data which is of great use to urban planners and infrastructure engineers. Informed decisions can then be taken to evolve existing and new infrastructure in a more robust and greener way. Data can be captured with the use of a single-camera tracker, which detects and tracks vehicles and pedestrians in the camera view. However, in more complex scenarios, such as a roundabout or intersection, the use of a single camera is not sufficient. For this study, a single-camera tracker, developed by Greenroads Ltd, is readily available [...] Description: M.Sc. ICT(Melit.) 2024-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/140265 Title: Detecting anomalies from roadside video streams Abstract: The interconnected nature of road networks implies that anomalies on narrow residential roads can ripple through the entire traffic system, particularly in high‐ traffic areas as common for the Maltese Islands. Detecting anomalies in such en‐ vironments using roadside cameras is challenging due to the multitude of normal and anomalous events, changes in illumination, obstructions, complex anomalies, and difficult viewing angles. This thesis investigates anomaly detection methods tailored to the realistic road and data limitations typical of Maltese urban roads. Classical anomaly detection, which identifies anomalies from structured data, and deep learning‐based techniques, which detect anomalies directly from video input, were evaluated. The literature review revealed limited evaluations on realistic datasets for both methods. The classical method was developed to filter out ID switch artifacts and identify specific anomalies using a combination of filtering, DBSCAN clustering, masking, and rule‐based techniques. For the deep learning method, an AE model with the STAE [1] architecture was chosen for its ability to capture temporal rep‐ resentation. Both methods were evaluated on video datasets collected in Malta and a relabeled Street Scene [2] dataset. The classical method demonstrated high reliability in detecting anomalies in structured data, achieving an 82% true positive rate and a 3% false positive rate for a local dataset. However, the data acquisition method did not accurately record all anomalies, reducing the true positive rate for actual video anomalies. The deep learning method showed strong performance across all datasets, achiev‐ ing an 83% AUC and a 25% EER for a dataset recorded in the same location. Per‐ formance was slightly reduced for locations with heavy shadows, as shown on a second local dataset. Segmenting frames into tiles and augmenting datasets improved performance in shadow‐affected conditions, as did masking irrelevant regions. An event‐level comparison showed both methods performed similarly in detecting non‐typical vehicle paths. The classical method excelled at identifying non‐typical object locations and was more robust against changes in scene dynam‐ ics, is more modular, and easier to debug. The deep learning method was better at detecting non‐typical slow‐moving and non‐typical vehicles and was more resilient to variations in the data acquisition method within the Intelligent Traffic System (ITS). However, neither method effectively detected unforeseen anomalies. Over‐ all, this thesis provides valuable insights and guidance for choosing the most ap‐ propriate anomaly detection methods tailored to different types of anomalies in complex urban road environments. Description: M.Sc. ICT(Melit.) 2024-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/135523 Title: Artificial intelligence for team sports Abstract: Football is one of the world’s most popular sports, with a massive fan base and a yearly revenue of billions of euros. Therefore, accurately predicting the outcomes of football matches has become a crucial task within the field of sports. It has always been a chal‐ lenging task to predict the outcome of a football match, not only for fans but also for experts like bookmakers. There are multiple factors that can significantly influence the result, including the team’s form throughout a season, weather conditions, and playing style. In this dissertation, we aim to provide a comprehensive overview of the differ‐ ent methods employed to predict football match outcomes through the implementation of machine learning algorithms, while also leveraging historical data. Machine learning models have proven to be highly effective in predicting the outcome of football matches since they take into account a wide range of factors. Furthermore, these models use historical data to uncover patterns and trends that can subsequently be used to make predictions. The goal of this dissertation is to predict the full‐time result of a football match. A prediction can be classified into three possible outcomes: win, draw, or loss. The first step in predicting the outcome of a match is to collect and preprocess the data. The data collected focuses on the English Premier League, which is widely recognised as one of the most popular leagues in the world. The data is sourced from Football‐Data, an open‐source platform. In total, four machine learning algorithms are employed, Lo‐ gistic Regression, Random Forest, Extreme Gradient Boosting, and Support Vector Ma‐ chine. These algorithms are trained using an 80:20 ratio split. Initially, a baseline model is defined, employing manual feature selection and default parameters. The accuracies achieved of the models ranged between 49.5% and 55.5%, with the Logistic Regression model performing the best. Then, we conducted an optimisation procedure to fine‐tune the parameters of the achieved models. This resulted in a 55% accuracy for the Sup‐ port Vector Machine model. In the next experiment, we introduced feature selection and dimensionality reduction techniques, such as Forward Feature Selection, and Prin‐ cipal Component Analysis, whilst also keeping the default parameters for each model. The accuracies achieved ranged between 86% and 90%, with the top performer being the Random Forest model. Furthermore, another experiment is performed by combin‐ ing these techniques with an exhaustive grid search to identify the optimal parameters for each model. The Extreme Gradient Boosting model achieved the best accuracy of 94%. Furthermore, besides accuracy, other evaluation metrics are considered to gain a more detailed understanding of the predictive performance of each model. We con‐ cluded that implementing appropriate techniques and selecting optimal parameters can significantly enhance predictive power. Description: M.Sc.(Melit.) 2024-01-01T00:00:00Z