1 - 5 of 49
- PublicationNavigating Academia – Recommender Systems for Module Exploration(University College Dublin. School of Computer Science, 2022)Personalised recommendations feature prominently in many aspects of our lives, from the movies we watch to the news we read and even the people we date. However, one area that is still relatively underdeveloped is the educational sector, where recommender systems have the potential to help students in a variety of ways, support- ing their decision making when choosing a suitable university programme, finding the right study material, and making informed choices about their learning pathways. This work focuses on recommender systems for academic advising, helping students find the most suitable modules. Today’s students enjoy various options regarding the availability of courses and modules, encouraging students to broaden their horizons, explore their interests and strengths, and develop new skills. One such opportunity offered in many universities is the possibility to freely choose elective modules from outside a student’s primary area of study. Taking such elective modules is often a requirement and can significantly impact students’ academic experience and overall performance. In this thesis, we explore how recommender systems, and content-based approaches, in particular, can be used to support students in finding suitable modules, shape their academic and career paths, as well as gain knowledge and make more informed decisions. Our approach is based on the textual descriptors that are freely available on universities module catalogues to match students with modules based on their learned interests and preferences. In contrast to the majority of related work in the field, our approaches work independently of students’ demographic, personal, and performance data. We show how the module descriptors can be used to extract module similarities and latent topics that allow for rich visualisation options and personalised module recommender systems. We evaluate our approach using offline and online studies. In a live user study, we show that our approach can improve student knowledge about their subject and elective module options. Furthermore, the results show that the participating students largely enjoy interacting with the system and show a high likeliness of reusing the system again in the future.
- PublicationDevelopment of a Ransomware Investigation Playbook for the Financial Sector, in compliance with ISO/IEC 27043(University College Dublin. School of Computer Science, 2022)Within the field of digital forensics, incident response and investigation, many groups have developed and evolved their own methods and procedures for conducting investigations of incidents in the digital space, until the creation of ISO/IEC 27043 in 2015. This was an attempt to harmonise existing methods into a single model, however the Standard is intentionally generalist and non-industry specific. This is why we have developed an augmented version tailored for the financial services sector, in the hope that this will assist the reader in both comprehending and implementing ISO/IEC 27043 within their own organisation, thus increasing compliance. Specifically, we have developed and evaluated a playbook for ransomware incident investigation that is practical without sacrificing compliance.
- PublicationData-driven Quality of Experience for Digital Audio Archives(University College Dublin. School of Computer Science, 2022)The digitization of sound archives began to safeguard records that naturally deteriorate due to the irreversible chemical processes of the sound carriers. The digitization process has improved the usability and accessibility of audio archives and provided the possibility of using digital restoration. Assessing the quality of digitization, restoration, and audio archive consumption is essential for evaluating sound archive practices. The state-of-the-art in digitization, restoration, and consumption of audio archives has neglected quality assessment approaches that are automatic and take into account the user's perspective. This thesis aims to understand and define the quality of experience (QoE) of sound archives and proposes data-driven objective metrics that can predict the QoE of music audio archives in the absence of human listeners. The author proposes a paradigm shift to deal with the problem of quality assessment in sound archives by focusing on quality metrics for musical signals based on deep learning which are developed and evaluated using annotations obtained with listening tests. The adaptation of the QoE framework for audio archive evaluation is proposed to consider the user's perspective and define QoE in sound archives. The author, in a case study of audio archive consumption, proposes a curated and annotated dataset of real-world music recordings from vinyl collections and three objective quality metrics. The thesis shows that annotating a dataset with real-world music recordings requires a different approach to prepare the stimuli and proposes a technique based on stratified random sampling from clusters. The three proposed quality metrics are based on learning feature representations with three different tasks: degradation classification, deep convolutional embedded clustering (DCEC), and self-supervised learning (SSL). The first two tasks are proposed using an architecture based on framewise convolutional neural networks, while the SSL task is based on pre-training and fine-tuning wav2vec 2.0 on musical signals. This thesis demonstrates that degradation classification, DCEC, and wav2vec 2.0 learn useful musical representations for predicting the quality of vinyl collections. More specifically, the proposed metrics overcome two baselines when fine-tuning small annotated sets. The author also proposes a new correlation-based feature representation for classifying audio carriers, which overcomes the raw feature representations in terms of speed and feature dimensionality. Classifying audio carriers can be used as a pre-step of the quality metrics mentioned above when predicting the quality of multiple collections. The significance of the proposed work is that audio archive metadata can be enriched by providing quality labels using the proposed metrics. Overall, the thesis encourages scholars and stakeholders to a paradigm shift when evaluating the quality of sound archives i.e. moving from a manual system-centric approach to a more automatic user-centric approach.
- PublicationEffective Deep Learning Based Methods for the Anomaly Detection in Software-Defined Networks(University College Dublin. School of Computer Science, 2022)In the traditional IP networks, the functionality of decision making processes known as control plane and the forwarding of network traffic (data plane) are implemented within the network devices (e.g. routers or switches). The network operators configure traffic policies (e.g. routing, switching, quality of service) on each device independently. However, the aforementioned architecture increases the operational costs and makes it challenging to adapt and maintain the network configurations security on-demand. Hence, Software-defined Networks (SDN) is an emerging networking paradigm, which has the characteristics to allow more flexibility in network management. SDN accelerates network innovation by centralising the control and visibility across the network (i.e. set policies and prioritise traffic through a centralised controller). However, security has become a serious concern which impedes the widespread adoption of SDN. The new network architecture introduces new potential attack surfaces that did not exist before or are harder to exploit. One of the most common and serious types of attacks is Distributed Denial of Service (DDoS) attack, which can prevent normal users from access their network services. ~If the attacker successfully floods the SDN controller with a massive number of requests, the entire network turns into a ‘body with no brain’. Therefore, detecting these attacks is considered one of the most essential topics for the anomaly detection community. Intrusion detection systems (IDSs) are the standard security solutions to protect the network from malicious activities. Recently, several Machine Learning (ML) approaches have been proposed to provide a framework for securing SDN networks from intrusion attacks. However, the current work that applied ML for intrusion detection depends heavily on feature engineering to choose the right feature set. The evolving nature of network attacks and the rapid change of the attacker techniques makes these methods not suitable for attack detection in real-time. Since learning the complex relationships among different features requires prior knowledge from experts, and thus it is problematic and susceptible to lag. Besides the aforementioned limitations, one of the main challenges in deployment of detection mechanisms is the lack of realistic datasets for SDN networks. Most of the research community uses intrusion detection datasets, which are generated for IP traditional networks. The objective of this research dissertation is to develop an efficient and effective intrusion detection technique using Deep Learning (DL) algorithms to detect malicious activities in the SDN architecture. Firstly, we solved the lack availability of intrusion detection datasets by producing a new specific dataset for SDNs. The dataset contains the new attacks, which are generated as a result of separating the control plane from the data plane. Secondly, we developed a new detection approach based on DL techniques (DDoSNet) to solve the problem of DDoS attacks in SDN networks. The proposed approach has combined the autoencoder with the long short term memory (LSTM) algorithm to improve the detection rate of the DL approaches. Thirdly, we develop a new detection method by using the convolutional neural network (CNN) to reduce the weight explosion of the traditional neural networks. A new regularisation technique based on standard deviation has been deployed to avoid the overfitting problem and enhance the model performance for unknown attacks. The experimental results show that the developed approach has the capability to detect the known and new attacks as well with high performance rate. Finally, we produce a new DL method based on semi-supervised learning to tackle the problem of unlabeled and unbalanced datasets for network traffic. The obtained results for all experiments approved the potential of DL algorithms in anomaly detection techniques.
- PublicationUser-centred Digital Health in Cardiovascular Rehabilitation and Self-management(University College Dublin. School of Computer Science, 2022)An acute cardiac incident is a life changing event and people face emotional and physical challenges during their transition from hospitalisation to self-management. Supervised rehabilitation programs, like, cardiac rehabilitation play a vital role in supporting this transition. Lack of knowledge, transportation, and motivation limits the uptake of such programs. Increasingly, sensor technologies providing patient-generated data are showing potential to overcome these limitations. But, evidence regarding its routine use and effectiveness is mixed and the commonly reported barriers include insufficient time, data lacking context, unfamiliar structure, misaligned objectives, usability, and reliability issues. Therefore, a greater understanding of patients’ experiences and factors that impact their behaviour after hospitalisation is needed to design such technologies. Also, to increase their success when deployed in real-world clinical contexts, designing by integrating both clinicians' and patients' perspectives is important. User-centred design approaches emphasise the importance of situating user experiences, needs, and preferences as the driver of the digital intervention design. Given the strong evidence from the field of human-computer interaction that user-centred and iterative design methods increase the success of digital health interventions, limited studies were identified that involved users in the design process and applied iterative methods. To contribute new insights to an area lacking in empirical research, this thesis applies the user- centred design methods and the co-design framework to design technology-mediated solutions to support cardiac rehabilitation and self-management. This thesis engages more directly with patients’ and clinicians’ post-hospitalisation experiences and the impact of patient-generated data through a series of studies. Four studies were conducted to achieve the aims of the thesis: a qualitative systematic grounded theory literature review; semi- structured interviews with cardiac patients; co-design study with cardiac rehabilitation clinicians; and field study for system deployment in real-world clinical context. Building on the collective findings of the studies conducted in this thesis, empirically grounded user-centred recommendations are presented to improve the design of technology-mediated support for CR and self-management. The key design recommendations presented in this thesis include: (i) the use of technology to support a normal life, leveraging social influences to extend participants’ sense of normality; (ii) the use of technology to provide both emotional and physical safe zoning; (iii) a focus on recognising capability and providing recommendations that are positive and reinforce this capability; (iv) supplementing objective data from consumer wearable devices with subjective patient experience data to enable meaningful and actionable insights for clinicians; (v) adopting structured approach to subjective data collection grounded in the clinicians’ workflow and co-designed with the clinicians to allow for such data to be shared in a familiar presentation; (vi) the importance of carefully considering the timing, type of App, context, and type of data presentation while sharing data between patients to avoid negative consequences and to empower patients to use technology to self-manage their condition.