Insight Centre for Data Analytics - Journal Articles

Permanent URI for this collection

https://hdl.handle.net/10468/5058

Browse

Now showing 1 - 5 of 122

A heuristic method for perishable inventory management under non-stationary demand
(Elsevier Ltd., 2025-01-07) Gulecyuz, Suheyl; O’Sullivan, Barry; Tarim, S. Armagan; Science Foundation Ireland
Our study considers a perishable inventory system under a finite planning horizon, periodic review, non-stationary stochastic demand, zero lead time, FIFO (first in, first out) issuing policy, and a fixed shelf life. The inventory system has a fixed setup cost and linear ordering, holding, penalty, and outdating costs per item. We introduce a computationally-efficient heuristic which formulates the problem as a network graph, and then calculates the shortest path in a recursive way and by keeping the average total cost per period at minimum. The heuristic firstly determines the replenishment periods and cycles using the deterministic-equivalent shortest path approach. Taking the replenishment plan constructed in the first step as an input, it calculates the order quantities with respect to the observed inventory states as a second step. We conduct numerical experiments for various scenarios and parameters, and compare them to the optimal stochastic dynamic programming (SDP) results. Our experiments conclude that the computation time is reduced significantly, and the average optimality gap between the expected total cost and the optimal cost is 1.87%.
Correlation between proprioception, functionality, patient-reported knee condition and joint acoustic emissions
(PLoS, 2024) Khokhlova, Liudmila; Komaris, Dimitrios-Sokratis; O’Flynn, Brendan; Tedesco, Salvatore; Science Foundation Ireland; European Regional Development Fund
Non-invasive assessment of joint status using acoustic emissions (AE) is a growing research area that has the potential to translate into clinical practice. The purpose of this study is to investigate the correlation of the knee’s AE with measures of proprioception, self-assessment, and performance, as it can be hypothesised that, AE parameters will correlate with joint function metrics due to AE being recorded during interaction of the articular surfaces. Threshold to detect passive motion (TTDPM), Knee Osteoarthritis Outcome Scores (KOOS) and 5 times sit-to-stand test (5STS) were collected from 51 participant. Knee AE were recorded during cycling with 30 and 60 rpm cadences using two sensors in different frequency ranges and three modes of AE event detection. Weak (0.297, p = 0.048) to moderate (0.475, p = 0.001) Spearman’s correlations were observed between longer 5STS time and AE parameters (i.e. higher median absolute energy, signal strength, longer AE event rise time and duration). Similarly, AE parameters shown correlation with lower KOOS, especially in the “Function in Sports and Recreation” and “Activities of Daily Living” subscales with correlation coefficients for higher median amplitude up to 0.441, p = 0.001 and 0.403, p = 0.004, respectively. The correlation with the TTDPM was not detected for most of the AE parameters. Additionally, a lower frequency sensor and 60 rpm cadence AE recordings showed higher correlations. Considering that this study included subjects from the general population and the number of participants with KOOS <70 was relatively small, higher correlations might be expected for clinically confirmed OA cases. Additionally, different ICCs might be expected for alternative signal parameters and proprioception assessment methods. Overall, the study confirms that AE monitoring offers an additional modality of joint assessment that reflects interaction between cartilage surfaces and can complement orthopaedic diagnostics, especially in the context of remote monitoring, drug testing, and rehabilitation.
A constraint-based parallel local search for the edge-disjoint rooted distance-constrained minimum spanning tree problem
(Springer Nature, 2017-06-16) Arbelaez, Alejandro; Mehta, Deepak; O’Sullivan, Barry; Quesada, Luis
Many network design problems arising in areas as diverse as VLSI circuit design, QoS routing, traffic engineering, and computational sustainability require clients to be connected to a facility under path-length constraints and budget limits. These problems can be seen as instances of the rooted distance-constrained minimum spanning-tree problem (RDCMST), which is NP-hard. An inherent feature of these networks is that they are vulnerable to a failure. Therefore, it is often important to ensure that all clients are connected to two or more facilities via edge-disjoint paths. We call this problem the edge-disjoint RDCMST (ERDCMST). Previous work on the RDCMST has focused on dedicated algorithms and therefore it is difficult to use these algorithms to tackle the ERDCMST. We present a constraint-based parallel local search algorithm for solving the ERDCMST. Traditional ways of extending a sequential algorithm to run in parallel perform either portfolio-based search in parallel or parallel neighbourhood search. Instead, we exploit the semantics of the constraints of the problem to perform multiple moves in parallel by ensuring that they are mutually independent. The ideas presented in this paper are general and can be adapted to other problems as well. The effectiveness of our approach is demonstrated by experimenting with a set of problem instances taken from real-world passive optical network deployments in Ireland, Italy, and the UK. Our results show that performing moves in parallel can significantly reduce the elapsed time and improve the quality of the solutions of our local search approach.
Solving complex optimisation problems by machine learning
(MDPI, 2024) Prestwich, Steven D.; Science Foundation Ireland; Horizon 2020
Most optimisation research focuses on relatively simple cases: one decision maker, one objective, and possibly a set of constraints. However, real-world optimisation problems often come with complications: they might be multi-objective, multi-agent, multi-stage or multi-level, and they might have uncertainty, partial knowledge or nonlinear objectives. Each has led to research areas with dedicated solution methods. However, when new hybrid problems are encountered, there is typically no solver available. We define a broad class of discrete optimisation problem called an influence program, and describe a lightweight algorithm based on multi-agent multi-objective reinforcement learning with sampling. We show that it can be used to solve problems from a wide range of literatures: constraint programming, Bayesian networks, stochastic programming, influence diagrams (standard, limited memory and multi-objective), and game theory (multi-level programming, Bayesian games and level-k reasoning). We expect it to be useful for the rapid prototyping of solution methods for new hybrid problems.
Radiomic study of antenatal prediction of severe placenta accreta spectrum from MRI
(Oxford University Press, 2024-08-17) Bartels, Helena C.; Wolsztynski, Eric; O'Doherty, Jim; Brophy, David P.; MacDermott, Roisin; Atallah, David; Saliba, Souha; El Kassis, Nadine; Moubarak, Malak; Young, Constance; Downey, Paul; Donnelly, Jennifer; Geoghegan, Tony; Brennan, Donal J.; Curran, Kathleen M.; National Maternity Hospital, Ireland; Science Foundation Ireland
Objectives: We previously demonstrated the potential of radiomics for the prediction of severe histological placenta accreta spectrum (PAS) subtypes using T2-weighted MRI. We aim to validate our model using an additional dataset. Secondly, we explore whether the performance is improved using a new approach to develop a new multivariate radiomics model. Methods: Multi-centre retrospective analysis was conducted between 2018 and 2023. Inclusion criteria: MRI performed for suspicion of PAS from ultrasound, clinical findings of PAS at laparotomy and/or histopathological confirmation. Radiomic features were extracted from T2-weighted MRI. The previous multivariate model was validated. Secondly, a 5-radiomic feature random forest classifier was selected from a randomized feature selection scheme to predict invasive placenta increta PAS cases. Prediction performance was assessed based on several metrics including area under the curve (AUC) of the receiver operating characteristic curve (ROC), sensitivity, and specificity. Results: We present 100 women [mean age 34.6 (±3.9) with PAS], 64 of whom had placenta increta. Firstly, we validated the previous multivariate model and found that a support vector machine classifier had a sensitivity of 0.620 (95% CI: 0.068; 1.0), specificity of 0.619 (95% CI: 0.059; 1.0), an AUC of 0.671 (95% CI: 0.440; 0.922), and accuracy of 0.602 (95% CI: 0.353; 0.817) for predicting placenta increta. From the new multivariate model, the best 5-feature subset was selected via the random subset feature selection scheme comprised of 4 radiomic features and 1 clinical variable (number of previous caesareans). This clinical-radiomic model achieved an AUC of 0.713 (95% CI: 0.551; 0.854), accuracy of 0.695 (95% CI 0.563; 0.793), sensitivity of 0.843 (95% CI 0.682; 0.990), and specificity of 0.447 (95% CI 0.167; 0.667). Conclusion: We validated our previous model and present a new multivariate radiomic model for the prediction of severe placenta increta from a well-defined, cohort of PAS cases. Advances in knowledge: Radiomic features demonstrate good predictive potential for identifying placenta increta. This suggests radiomics may be a useful adjunct to clinicians caring for women with this high-risk pregnancy condition.

Browse

Recent Submissions