Computer Science - Doctoral Theses

Permanent URI for this collection


Recent Submissions

Now showing 1 - 5 of 73
  • Item
    Intelligibility of music playlists
    (University College Cork, 2023) Gabbolini, Giovanni; Bridge, Derek G.; Science Foundation Ireland
    A common strategy for organising music is by arranging songs in a playlist to obtain a continuous and thematic music flow. Playlists are popular in music streaming services, where 58% of the listeners construct their own playlists. The flip side of popularity is content-overload; streaming services currently host billions of playlists. The commercial value of playlists has attracted notable research efforts during the last two decades. Much of the research on playlists is concerned with automatically constructing playlists. This dissertation is on playlists, but on a topic complementary to constructing playlists. Our concern here is on describing playlists, so that playlists can be understood by a human audience, i.e. so that they become intelligible. The way we achieve intelligibility is by developing algorithms that can generate textual annotations, both at playlist level and at song level. At playlist level, an annotation can be text (e.g. a tag or a caption) that describes the playlist as a whole; at song level, an annotation can be text that describes the transition between two consecutive songs in the playlist. The purpose of intelligibility is that of facilitating music organisation & access, as well as enhancing the listen- ing experience of users, two goals particularly relevant in a content overload scenario. We propose five algorithms for playlist-level intelligibility, and three algorithms for song-level intelligibility. We are particularly interested in the user experi- ence, so we test the algorithms, in most cases, with both offline experiments and user trials. We find evidence that the algorithms can help accomplish the two goals of intelligibility, i.e. enhancing listening experiences, and facilitating organisation and access. We pair the algorithms with a comprehensive survey of MIR research on music playlists, which provide a useful framework for understanding our contributions in the context of a broad selection of related research.
  • Item
    Leveraging network state for software-defined data centre network management
    (University College Cork, 2023) Sherwin, Jonathan; Sreenan, Cormac J.; Munster Technological University
    This work addresses key aspects in the management of a software-defined multi-tenant Data Centre Network (DCN). Software-defined networking (SDN) offers significant potential benefit for many aspects of DCN management – e.g. configuration, monitoring, performance and utilisation, and security – and many researchers have worked, successfully, over the last number of years to show how improvements to these areas could be achieved. The insight that motivated this work is that the focus by researchers and tool vendors has been on managing the current state or desired future state of the DCN. Meanwhile, issues relating to reviewing, analysing and evaluating the past state of a software-defined DCN have been neglected. SDN has been essential for DCNs to meet the requirements of a multi-tenant cloud environment - through automated, dynamic reconfiguration of network devices and services to accommodate tenants arriving, leaving, and modifying their resource requirements via a self-service interface. Consequently, a DCN operator cannot be expected to know the current state of the network, let alone past states, without tools to query the network and provide that information. DCN operators are well served by tools to manage and query the current state of an SDN, but not previous network states and events. The research question addressed in this work is how to record the topological and configuration history of a DCN, present a useful view of that historical record to the DCN operator, and provide the means for the operator to query the historical DCN state. A related question is how to employ SDN itself to improve the performance of a software-defined DCN. Solving these issues is challenging because of the scale of a DCN (potentially scaling to hundreds of switches connecting thousands of devices), the constantly changing configuration of a multi-tenant software-defined DCN, and the duration of months or years over which the history must be recorded, analysed and available for querying. The selected approach takes advantage of the decoupled nature of the control- and data-planes in SDN, to eavesdrop on communications between an SDN controller and switches. Emulated and conceptual models of a DCN have been created from key information extracted from the captured communications. The conceptual model relies on a combination of new and existing ontologies, with an extensible set of concepts and relationships that are the target of complex operator-focussed queries. The contributions of the work are as follows: 1. Accurate reproduction of an emulated copy of a DCN (topology and state) for any time in its history solely from a passively captured log of control-plane messages. 2. The use of snapshots to speed up the reproduction time of an emulated DCN with topology and state for a particular point in time. 3. Use of an ontological approach to creating a temporal and topological model of a DCN, populated solely from a log of control-plane messages, and created for the purpose of answering operator queries. 4. A methodology to develop additional sophisticated queries against the ontological model regarding the historical state of and events on a DCN. 5. A method to improve the veracity of control-plane messages by reducing the latency of interactions between SDN controllers and hardware switches in a DCN.
  • Item
    Metaheuristics and machine learning for joint stratification and sample allocation in survey design
    (University College Cork, 2022-01) O'Luing, Mervyn; Prestwich, Steve; Tarim, Armagan; European Regional Development Fund; Science Foundation Ireland
    In this thesis, we propose a number of metaheuristics and machine learning techniques to solve the joint stratification and sample allocation problem. Finding the optimal solution to this problem is hard when the sampling frame is large, and the evaluation algorithm is computationally burdensome. To advance the research in this area, we explore and evaluate different algorithmic methods of modelling and solving this problem. Firstly, we propose a new genetic algorithm approach using "grouping" genetic operators instead of traditional operators. Experiments show a significant improvement in solution quality for similar computational effort. Next, we combine the capability of a simulated annealing algorithm to escape from local minima with delta evaluation to exploit the similarity between consecutive solutions and thereby reduce evaluation time. Comparisons with two recent algorithms show the simulated annealing algorithm attaining comparable solution qualities in less computation time. Then, we consider the combination of the k-means and clustering algorithms with a hill climbing algorithm in stages and report the solution costs, evaluation times and training times. The multi-stage combinations generally compare well with recent algorithms, and provide the survey designer with a greater choice of algorithms to choose from. Finally, we combine the explorative properties of an estimation of distribution algorithm (EDA) to model the probabilities of an atomic stratum belonging to different strata with the exploitative search properties of a simulated annealing algorithm to create a hybrid estimation of distribution algorithm (HEDA). Results of comparisons with the best solution qualities from our earlier experiments show that the HEDA finds better solution qualities, but requires a longer total execution time than alternative approaches we considered.
  • Item
    Beyond gangsta: hip-hop, web culture and racial masking in the musical work of Tyler, The Creator
    (University College Cork, 2021-09-14) Marques, Gustavo Souva; Rollefson, J. Griffith; Kulezic-Wilson, Danijela; Alves da Silva, Rubens
    Tyler, The Creator (Tyler Gregory Okonma), is an African American rapper, music producer and entrepreneur who has been vigorously challenging tropes of black American masculinity. From chattel slavery to blackface minstrelsy, the African diasporic experience in the West is marked by a series of stigmas, contradictions and dichotomies evidenced in the challenge of being black in a white world. This duplicity denounced and analyzed by scholars such as W.E.B. DuBois and Frantz Fanon informs the theoretical frame of this dissertation but also reflects Tyler’s investments in subverting American racial ideology in his controversial audio-visual performances. Through his participation in and appropriating of skateboarding and web culture, Tyler denies common associations and stereotypes of blackness related to gangsterism which allowed him to become an internet phenomenon at the age of 19 with his music video “Yonkers” (2011). This study analyzes Tyler’s systematic move beyond gangsta through close media analysis and through ethnographic work in and around the black suburbia of Tyler’s upbringing in Southern California.
  • Item
    Autonomous system control in unknown operating conditions
    (University College Cork, 2021-08-24) Sohège, Yves; Provan, Gregory; Tabirca, Marius-Sabin; Science Foundation Ireland
    Autonomous systems have become an interconnected part of everyday life with the recent increases in computational power available for both onboard computers and offline data processing. The race by car manufacturers for level 5 (full) autonomy in self-driving cars is well underway and new flying taxi service startups are emerging every week, attracting billions in investments. Two main research communities, Optimal Control and Reinforcement Learning stand out in the field of autonomous systems, each with a vastly different perspective on the control problem. Controllers from the optimal control community are based on models and can be rigorously analyzed to ensure the stability of the system is maintained under certain operating conditions. Learning-based control strategies are often referred to as model-free and typically involve training a neural network to generate the required control actions through direct interactions with the system. This greatly reduces the design effort required to control complex systems. One common problem both learning- and model- based control solutions face is the dependency on a priori knowledge about the system and operating conditions such as possible internal component failures and external environmental disturbances. It is not possible to consider every possible operating scenario an autonomous system can encounter in the real world at design time. Models and simulators are approximations of reality and can only be created for known operating conditions. Autonomous system control in unknown operating conditions, where no a priori knowledge exists, is still an open problem for both communities and no control methods currently exist for such situations. Multiple model adaptive control is a modular control framework that divides the control problem into supervisory and low-level control, which allows for the combination of existing learning- and model-based control methods to overcome the disadvantages of using only one of these. The contributions of this thesis consist of five novel supervisory control architectures, which have been empirically shown to improve a system’s robustness to unknown operating conditions, and a novel low- level controller tuning algorithm that can reduce the number of required controllers compared to traditional tuning approaches. The presented methods apply to any autonomous system that can be controlled using model-based controllers and can be integrated alongside existing fault-tolerant control systems to improve robustness to unknown operating conditions. This impacts autonomous system designers by providing novel control mechanisms to improve a system’s robustness to unknown operating conditions.