Yazar "Firouz, Mohammad" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    An Adaptive Simulated Annealing-Based Machine Learning Approach for Developing an E-Triage Tool for Hospital Emergency Operations
    (Springer, 2023) Ahmed, Abdulaziz; Al-Maamari, Mohammed; Firouz, Mohammad; Delen, Dursun
    Patient triage at emergency departments (EDs) is necessary to prioritize care for patients with critical and time-sensitive conditions. In this paper, the metaheuristic optimization algorithms simulated annealing (SA) and adaptive simulated annealing (ASA) are proposed to optimize the parameters of extreme gradient boosting (XGB) and categorical boosting (CaB). The proposed algorithms are SA-XGB, ASA-XGB, SA-CaB, and ASA-CaB. Grid search (GS), a traditional approach used for machine learning fine-tuning, is also used to fine-tune the parameters of XGB and CaB, which are named GS-XGB and GS-CaB. The optimized model is used to develop an e-triage tool that can be used at EDs to predict ED patients' emergency severity index (ESI). The results show ASA-CaB outperformed all the proposed algorithms with accuracy, precision, recall, and f1 of 83.3%, 83.2%, 83.3%, and 83.2%, respectively.
  • Küçük Resim Yok
    Öğe
    On the Egalitarian-Utilitarian spectrum in stochastic capacitated resource allocation problems
    (Elsevier, 2023) Li, Linda; Firouz, Mohammad; Ahmed, Abdulaziz; Delen, Dursun
    In this paper, we study a generalized resource allocation problem where a limited resource is to be allocated to a set of agencies with stochastic receiving capacities while taking into account the decision-maker's preference towards equity in allocation. Taking the empiric distributional nature of the capacities into account, we formulate the problem in a chance-constrained based Mixed-Integer Programming framework with user -specified reliability and tolerance levels as well as equity preference level. We show that the problem can be conveniently reduced to a linear equivalent with adjusted capacity constraints. Deriving the tightest lower and upper bounds corresponding to the utilitarian and egalitarian perspectives, respectively, we give the closed -form optimal solutions for such cases. Using real data, we test the behavior of our model with a view towards the inherent equity-efficiency as well as reliability-efficiency trade-offs. We further characterize the cost and value of information in a detailed analysis.