arXiv subjects

Conor O'Sullivan

Publications and source records attributed to Conor O'Sullivan.

7 recordsLinked to original sources

arXiv2025

Who Is Lagging Behind: Profiling Student Behaviors with Graph-Level Encoding in Curriculum-Based Online Learning Systems

The surge in the adoption of Intelligent Tutoring Systems (ITSs) in education, while being integral to curriculum-based learning, can inadvertently exacerbate performance gaps. To address this problem, student profiling becomes crucial for tracking progress, identifying struggling students, and alleviating disparities among students. Such profiling requires measuring student behaviors and performance across different aspects, such as content coverage, learning intensity, and proficiency in different concepts within a learning topic. In this study, we introduce CTGraph, a graph-level representation learning approach to profile learner behaviors and performance in a self-supervised manner. Our experiments demonstrate that CTGraph can provide a holistic view of student learning journeys, accounting for different aspects of student behaviors and performance, as well as variations in their learning paths as aligned to the curriculum structure. We also show that our approach can identify struggling students and provide comparative analysis of diverse groups to pinpoint when and where students are struggling. As such, our approach opens more opportunities to empower educators with rich insights into student learning journeys and paves the way for more targeted interventions.

cs.AI↗

arXiv2024

Graph Reconstruction via MIS Queries

In the Graph Reconstruction (GR) problem, a player initially only knows the vertex set $V$ of an input graph $G=(V, E)$ and is required to learn its set of edges $E$. To this end, the player submits queries to an oracle and must deduce $E$ from the oracle's answers. In this paper, we initiate the study of GR via Maximal Independent Set (MIS) queries, a more powerful variant of Independent Set (IS) queries. Given a query $U \subseteq V$, the oracle responds with any, potentially adversarially chosen, maximal independent set $I \subseteq U$ in the induced subgraph $G[U]$. We show that, for GR, MIS queries are strictly more powerful than IS queries when parametrized by the maximum degree $Δ$ of the input graph. We give tight (up to poly-logarithmic factors) upper and lower bounds for this problem: 1. We observe that the simple strategy of taking uniform independent random samples of $V$ and submitting those to the oracle yields a non-adaptive randomized algorithm that executes $O(Δ^2 \cdot \log n)$ queries and succeeds with high probability. Furthermore, combining the strategy of taking uniform random samples of $V$ with the probabilistic method, we show the existence of a deterministic non-adaptive algorithm that executes $O(Δ^3 \cdot \log(\frac{n}Δ))$ queries. 2. Regarding lower bounds, we prove that the additional $Δ$ factor when going from randomized non-adaptive algorithms to deterministic non-adaptive algorithms is necessary. We show that every non-adaptive deterministic algorithm requires $Ω(Δ^3 / \log^2 Δ)$ queries. For arbitrary randomized adaptive algorithms, we show that $Ω(Δ^2)$ queries are necessary in graphs of maximum degree $Δ$, and that $Ω(\log n)$ queries are necessary, even when the input graph is an $n$-vertex cycle.

cs.DS↗

arXiv2024

Enhancing coastal water body segmentation with Landsat Irish Coastal Segmentation (LICS) dataset

Ireland's coastline, a critical and dynamic resource, is facing challenges such as erosion, sedimentation, and human activities. Monitoring these changes is a complex task we approach using a combination of satellite imagery and deep learning methods. However, limited research exists in this area, particularly for Ireland. This paper presents the Landsat Irish Coastal Segmentation (LICS) dataset, which aims to facilitate the development of deep learning methods for coastal water body segmentation while addressing modelling challenges specific to Irish meteorology and coastal types. The dataset is used to evaluate various automated approaches for segmentation, with U-NET achieving the highest accuracy of 95.0% among deep learning methods. Nevertheless, the Normalised Difference Water Index (NDWI) benchmark outperformed U-NET with an average accuracy of 97.2%. The study suggests that deep learning approaches can be further improved with more accurate training data and by considering alternative measurements of erosion. The LICS dataset and code are freely available to support reproducible research and further advancements in coastal monitoring efforts.

cs.CV↗

arXiv2024

Automated Coastline Extraction Using Edge Detection Algorithms

We analyse the effectiveness of edge detection algorithms for the purpose of automatically extracting coastlines from satellite images. Four algorithms - Canny, Sobel, Scharr and Prewitt are compared visually and using metrics. With an average SSIM of 0.8, Canny detected edges that were closest to the reference edges. However, the algorithm had difficulty distinguishing noisy edges, e.g. due to development, from coastline edges. In addition, histogram equalization and Gaussian blur were shown to improve the effectiveness of the edge detection algorithms by up to 1.5 and 1.6 times respectively.

cs.CV↗

arXiv2024

The Effectiveness of Edge Detection Evaluation Metrics for Automated Coastline Detection

We analyse the effectiveness of RMSE, PSNR, SSIM and FOM for evaluating edge detection algorithms used for automated coastline detection. Typically, the accuracy of detected coastlines is assessed visually. This can be impractical on a large scale leading to the need for objective evaluation metrics. Hence, we conduct an experiment to find reliable metrics. We apply Canny edge detection to 95 coastline satellite images across 49 testing locations. We vary the Hysteresis thresholds and compare metric values to a visual analysis of detected edges. We found that FOM was the most reliable metric for selecting the best threshold. It could select a better threshold 92.6% of the time and the best threshold 66.3% of the time. This is compared RMSE, PSNR and SSIM which could select the best threshold 6.3%, 6.3% and 11.6% of the time respectively. We provide a reason for these results by reformulating RMSE, PSNR and SSIM in terms of confusion matrix measures. This suggests these metrics not only fail for this experiment but are not useful for evaluating edge detection in general.

cs.CV↗

arXiv2024

Interpreting a Semantic Segmentation Model for Coastline Detection

We interpret a deep-learning semantic segmentation model used to classify coastline satellite images into land and water. This is to build trust in the model and gain new insight into the process of coastal water body extraction. Specifically, we seek to understand which spectral bands are important for predicting segmentation masks. This is done using a permutation importance approach. Results show that the NIR is the most important spectral band. Permuting this band lead to a decrease in accuracy of 38.12 percentage points. This is followed by Water Vapour, SWIR 1, and Blue bands with 2.58, 0.78 and 0.19 respectively. Water Vapour is not typically used in water indices and these results suggest it may be useful for water body extraction. Permuting, the Coastal Aerosol, Green, Red, RE1, RE2, RE3, RE4, and SWIR 2 bands did not decrease accuracy. This suggests they could be excluded from future model builds reducing complexity and computational requirements.

cs.LG↗

arXiv2019

Predicting the Outcome of Judicial Decisions made by the European Court of Human Rights

In this study, machine learning models were constructed to predict whether judgments made by the European Court of Human Rights (ECHR) would lead to a violation of an Article in the Convention on Human Rights. The problem is framed as a binary classification task where a judgment can lead to a "violation" or "non-violation" of a particular Article. Using auto-sklearn, an automated algorithm selection package, models were constructed for 12 Articles in the Convention. To train these models, textual features were obtained from the ECHR Judgment documents using N-grams, word embeddings and paragraph embeddings. Additional documents, from the ECHR, were incorporated into the models through the creation of a word embedding (echr2vec) and a doc2vec model. The features obtained using the echr2vec embedding provided the highest cross-validation accuracy for 5 of the Articles. The overall test accuracy, across the 12 Articles, was 68.83%. As far as we could tell, this is the first estimate of the accuracy of such machine learning models using a realistic test set. This provides an important benchmark for future work. As a baseline, a simple heuristic of always predicting the most common outcome in the past was used. The heuristic achieved an overall test accuracy of 86.68% which is 29.7% higher than the models. Again, this was seemingly the first study that included such a heuristic with which to compare model results. The higher accuracy achieved by the heuristic highlights the importance of including such a baseline.

cs.LG↗